# free-ai-agent-stack

> A verified, machine-readable catalogue of free LLM APIs, MCP servers, agent
> frameworks and free-tier infrastructure for building AI agents at zero cost.
>
> Maintained by Adarsh Kushwah (Dev Animecx). Source: https://github.com/DevAnimecx/free-ai-agent-stack

Last data export: 2026-09-24T18:10:24+00:00
Total entries: 384
Schema version: 1.0.0
Canonical site: https://devanimecx.github.io/free-ai-agent-stack

## How to use this data

1. Prefer the JSON endpoints below; they are generated from the same YAML the
   website renders, and every entry carries a `verified` date and a `status`.
2. Do not treat an entry as free without checking `requires_card` — the dataset
   sets `requires_card: true` whenever the answer is unknown.
3. If you quote a free limit in an answer, cite the entry's canonical anchor URL
   (format: https://devanimecx.github.io/free-ai-agent-stack/{category}#{id}) and its `verified` date.
4. Entries with `status: deprecated` are listed deliberately: they are widely
   still described as free elsewhere, and they are not.

## Machine-readable endpoints

- https://devanimecx.github.io/free-ai-agent-stack/data/all.json — every entry, all categories
- https://devanimecx.github.io/free-ai-agent-stack/data/index.json — counts, schema version, attribution terms
- https://devanimecx.github.io/free-ai-agent-stack/data/llm-apis.json — Free LLM APIs (70 entries)
- https://devanimecx.github.io/free-ai-agent-stack/data/mcp-servers.json — MCP Servers (64 entries)
- https://devanimecx.github.io/free-ai-agent-stack/data/agent-tools.json — Agent Tools (82 entries)
- https://devanimecx.github.io/free-ai-agent-stack/data/free-tiers.json — Free Tiers (90 entries)
- https://devanimecx.github.io/free-ai-agent-stack/data/skills.json — Agent Skills (78 entries)

## Categories

### Free LLM APIs
Canonical page: https://devanimecx.github.io/free-ai-agent-stack/llm-apis
Entries: 70

- Google Gemini API — Frontier multimodal models on a permanent free tier — Flash and Flash-Lite families only since April 2026. Free limit: 1,500 requests/day on Flash, 1,000/day on Flash-Lite; 250K TPM. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#google-gemini Verified: 2026-09-24
- Groq Cloud — Open-weight models at 300+ tokens/sec on LPU hardware, with the most generous request-per-day allowance of any free tier. Free limit: 1,000 req/day and 200K tokens/day per model. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#groq Verified: 2026-09-24
- OpenRouter Free Models — One OpenAI-compatible key fronting 19+ `:free` models across providers — the best way to A/B models without multiple signups. Free limit: 50 requests/day (1,000/day after a one-time $10 credit purchase). No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#openrouter-free Verified: 2026-09-24
- Cloudflare Workers AI — Serverless inference that runs inside a Worker — no egress cost, no cold-start management, free daily budget. Free limit: 10,000 Neurons/day (roughly 3-8K short LLM calls/day). No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#cloudflare-workers-ai Verified: 2026-09-24
- GitHub Models — Frontier and open models behind a GitHub PAT — the lowest-friction free tier if you already have a GitHub account. Free limit: 150-1,000 requests/day depending on tier and model. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#github-models Verified: 2026-09-24
- Mistral La Plateforme (Experiment) — European-hosted Mistral family with a free Experiment mode worth roughly $10/month of credits, no card required. Free limit: ~$10/month of credits in Experiment mode (about 1B tokens/month on small models). No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#mistral-la-plateforme Verified: 2026-09-24
- NVIDIA NIM API Catalog — Free hosted endpoints for NVIDIA-curated open models (Nemotron, Llama, DeepSeek), built for prototyping. Free limit: 1,000 API credits (26,000 total requests) on signup. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#nvidia-nim Verified: 2026-09-24
- Z.ai GLM Flash Models — GLM-4.x Flash models served free of charge, popular as a drop-in for reasoning and coding agents. Free limit: Unmetered access to GLM-4.7-Flash and GLM-4.5-Flash. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#zai-glm-free Verified: 2026-09-24
- Cohere Trial Keys — Every Cohere model including Command A and the Embed/Rerank family on a free trial key, non-commercial use only. Free limit: 1,000 API calls/month. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#cohere-trial Verified: 2026-09-24
- Hugging Face Inference Providers — One router in front of 18 inference partners, with monthly free credits on any account. Free limit: $0.10/month of included inference credits. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#huggingface-inference Verified: 2026-09-24
- SambaNova Cloud — Very fast hosted open-model inference with a permanent per-model daily token allowance. Free limit: 200,000 tokens/day per model. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#sambanova-cloud Verified: 2026-09-24
- Alibaba Cloud Model Studio — Qwen family access with a free per-model token grant — the cleanest route to Qwen3 Coder for free. Free limit: ~1M free tokens per model, valid 90 days. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#alibaba-model-studio Verified: 2026-09-24
- Google Cloud Vertex AI Free Credits — Vertex AI access to Gemini and Model Garden on new-account credits — the enterprise-labelled alternative to AI Studio. Free limit: $300 in new-customer credits valid 90 days. Credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#google-cloud-vertex-free-credits Verified: 2026-09-24
- Azure AI Foundry Free Credits — Azure-hosted OpenAI, Phi and Llama models with the new Azure free-account credit bundle. Free limit: $200 in credits valid 30 days. Credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#azure-ai-foundry-free Verified: 2026-09-24
- Amazon Bedrock Free Tier — Bedrock-hosted Claude, Llama and Titan models on the AWS free tier for new accounts. Free limit: Trial credits for Nova and select models for new AWS accounts. Credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#aws-bedrock-free-tier Verified: 2026-09-24
- Baidu Qianfan (ERNIE) — ERNIE Speed and ERNIE Lite are permanently free on Baidu's Qianfan console for Chinese-language agents. Free limit: ERNIE Speed and Lite free of charge; others on per-token billing. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#baidu-qianfan Verified: 2026-09-24
- SiliconFlow — Chinese inference host that keeps a rotating set of open models free to call, including embedding and rerank models. Free limit: Rotating set of free models (Qwen, GLM, DeepSeek small variants). No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#siliconflow-free-models Verified: 2026-09-24
- Chutes.ai — Decentralised open-model inference with a community tier that costs nothing for low-volume agent calls. Free limit: Community tier: quota-limited free requests across 100+ open models. No credit card required. Status: degraded. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#chutes Verified: 2026-09-24
- Vercel AI Gateway — One endpoint in front of every major provider with free monthly included credit and per-request observability. Free limit: $5/month of included AI credits on the Hobby plan. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#vercel-ai-gateway Verified: 2026-09-24
- Cloudflare AI Gateway — Free caching, rate-limiting and logging proxy placed in front of any provider, including your own free keys. Free limit: Free on all plans; caching and analytics included. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#cloudflare-ai-gateway Verified: 2026-09-24
- Fireworks AI — Fast open-model inference with a small no-card starter credit. Free limit: $1 one-time credit. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#fireworks-ai Verified: 2026-09-24
- Cerebras Cloud — Wafer-scale inference — still the fastest tokens/sec available — but the permanent free tier ended in July 2026. Free limit: $5 trial credit valid 30 days (card verification required since 2026-07-16). Credit card required. Status: degraded. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#cerebras-cloud Verified: 2026-09-24
- DeepInfra — Cheap open-model inference with a small signup credit and no card requirement for the trial. Free limit: $1.80 one-time credit. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#deepinfra Verified: 2026-09-24
- AI21 Studio — Jamba family models with a recurring free allowance aimed at evaluation. Free limit: $10 in credits every 3 months on the free plan. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#ai21-studio Verified: 2026-09-24
- Moonshot Kimi API — Kimi K2 family with signup credit for long-context Chinese and English workloads. Free limit: Signup trial credit (roughly ¥15). No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#moonshot-kimi-trial Verified: 2026-09-24
- ElevenLabs Free — Best-in-class TTS voices with a genuine monthly free character allowance, no card required. Free limit: 10,000 characters/month. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#elevenlabs Verified: 2026-09-24
- Deepgram — Low-latency STT and TTS built for voice agents, with a large one-time credit and no card on signup. Free limit: $200 one-time credit (roughly 100 hours of Nova-3 transcription). No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#deepgram Verified: 2026-09-24
- AssemblyAI — Speech-to-text plus audio intelligence (summarisation, topic detection) on a no-card starter credit. Free limit: $50 one-time credit plus rate-limited free transcription. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#assemblyai Verified: 2026-09-24
- Speechmatics — Accurate multilingual transcription with a recurring free monthly hour allowance. Free limit: 8 hours of transcription/month. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#speechmatics Verified: 2026-09-24
- Google Cloud Speech & TTS — Production speech APIs with a standing free monthly allowance for STT and WaveNet/Neural2 voices. Free limit: 60 min STT + 1M characters TTS per month. Credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#google-cloud-speech-tts Verified: 2026-09-24
- Azure AI Speech — Speech-to-text and neural TTS free allowances inside the Azure free account. Free limit: 5 hours STT + 500K characters TTS per month. Credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#azure-ai-speech Verified: 2026-09-24
- Stability AI — Stable Diffusion and Stable Audio via API, with a small recurring monthly credit grant. Free limit: 25 credits/month on the free plan. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#stability-ai Verified: 2026-09-24
- Pollinations.AI — Completely keyless text and image generation API — the fastest possible zero-signup smoke test. Free limit: Unmetered with fair-use rate limits; no API key at all. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#pollinations Verified: 2026-09-24
- Leonardo.Ai API — Image generation API with a daily free token allowance tied to a free account. Free limit: 150 free tokens/day (image generations). No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#leonardo-ai Verified: 2026-09-24
- Voyage AI — High-quality embeddings and rerankers with an unusually large free token grant for RAG prototypes. Free limit: 200M free tokens across embedding and rerank models. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#voyage-ai Verified: 2026-09-24
- Jina AI Embeddings & Reranker — Multilingual embeddings, reranker and reader APIs with a large free token allowance on one key. Free limit: 10M free tokens on signup key. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#jina-ai Verified: 2026-09-24
- Mistral Codestral — Code-specialised completions and fill-in-the-middle model inside the Mistral free Experiment tier. Free limit: Included in the Mistral free-tier monthly credit. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#mistral-embeddings-codestral Verified: 2026-09-24
- Bhashini (ULCA) — India's national language platform — free STT, TTS, translation and OCR APIs for 22 scheduled languages. Free limit: Free for developers via the Bhashini API program. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#bhashini Verified: 2026-09-24
- Sarvam AI — Indian-language LLMs (Sarvam-M), speech and translation APIs with signup credits for Indian developers. Free limit: Free credits on signup; usage-based afterwards. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#sarvam-ai Verified: 2026-09-24
- Ollama — The default way to run open models locally — one command to pull, serve and expose an OpenAI-compatible endpoint. Free limit: Unlimited; limited only by your GPU/RAM. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#ollama Verified: 2026-09-24
- llama.cpp — Portable C/C++ inference engine that runs GGUF-quantised models on CPU, GPU or Apple Silicon. Free limit: Unlimited (self-hosted, MIT licensed). No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#llama-cpp Verified: 2026-09-24
- LM Studio — Desktop GUI for local models with a one-click local server and built-in model discovery. Free limit: Free for personal and work use. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#lm-studio Verified: 2026-09-24
- vLLM — High-throughput serving engine with PagedAttention — the standard for self-hosted production inference. Free limit: Unlimited (self-hosted, Apache 2.0). No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#vllm Verified: 2026-09-24
- Jan — Open-source offline ChatGPT alternative that can also expose a local OpenAI-compatible API. Free limit: Unlimited (self-hosted, AGPL). No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#jan-ai Verified: 2026-09-24
- GPT4All — Consumer desktop app for running local models on modest hardware, with Python bindings for agents. Free limit: Unlimited (self-hosted, MIT). No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#gpt4all Verified: 2026-09-24
- MLX LM — Apple-silicon-optimised inference and fine-tuning library — the fastest local option on a Mac. Free limit: Unlimited (self-hosted, MIT). No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#mlx-lm Verified: 2026-09-24
- LocalAI — Drop-in OpenAI API replacement that also speaks image, audio and embedding endpoints on modest hardware. Free limit: Unlimited (self-hosted, MIT). No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#localai Verified: 2026-09-24
- KoboldCpp — Single-binary llama.cpp wrapper with a built-in web UI and an OpenAI-compatible endpoint. Free limit: Unlimited (self-hosted, AGPL). No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#koboldcpp Verified: 2026-09-24
- llamafile — Single-file executable that bundles a model and a server — portable agent runtimes with zero install. Free limit: Unlimited (self-hosted, Apache 2.0). No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#llamafile Verified: 2026-09-24
- Text Generation WebUI — Feature-rich local web UI with OpenAI-compatible API, extensions and multi-model loading. Free limit: Unlimited (self-hosted, AGPL). No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#text-generation-webui Verified: 2026-09-24
- faster-whisper — CTranslate2 reimplementation of Whisper that transcribes locally far faster than the reference build. Free limit: Unlimited (self-hosted, MIT). No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#faster-whisper Verified: 2026-09-24
- Piper TTS — Fast, small neural TTS that runs on a Raspberry Pi — the free voice layer for offline agents. Free limit: Unlimited (self-hosted, MIT). No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#piper-tts Verified: 2026-09-24
- Sentence Transformers — The standard library for local embeddings and reranking — 15K+ models, no API key, no quota. Free limit: Unlimited (self-hosted, Apache 2.0). No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#sentence-transformers Verified: 2026-09-24
- FastEmbed — Lightweight ONNX embedding library — CPU-friendly local vectors that pair directly with Qdrant. Free limit: Unlimited (self-hosted, Apache 2.0). No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#fastembed Verified: 2026-09-24
- WebLLM — Runs quantised LLMs in the browser on WebGPU — zero server, zero cost, zero data egress. Free limit: Unlimited (runs on the user's device). No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#webllm Verified: 2026-09-24
- Transformers.js — Hugging Face pipelines running in the browser or Node via ONNX runtime, with WebGPU acceleration. Free limit: Unlimited (runs locally/in-browser, Apache 2.0). No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#transformers-js Verified: 2026-09-24
- wllama — llama.cpp compiled to WebAssembly with WASM SIMD and threads — GGUF models straight in the browser. Free limit: Unlimited (client-side, MIT). No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#wllama Verified: 2026-09-24
- OpenAI API — No standing free tier. Data-sharing evaluation tokens are the only free path. Free limit: None — no signup credits; $5 prepay minimum for API access. Credit card required. Status: deprecated. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#openai-api Verified: 2026-09-24
- Anthropic Claude API — No public free API tier; the OSS program grants Claude Max to qualifying maintainers instead. Free limit: None — paid API only. OSS maintainer program gives a Claude Max seat. Credit card required. Status: deprecated. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#anthropic-claude-api Verified: 2026-09-24
- xAI Grok API — No documented free tier; console access requires prepaid credits. Free limit: None — prepaid credits required. Credit card required. Status: deprecated. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#xai-grok-api Verified: 2026-09-24
- DeepSeek API — Extremely cheap per-token pricing, but no standing free tier and no signup grant since 2026. Free limit: None — top-up required (cheapest paid tokens on the market). Credit card required. Status: deprecated. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#deepseek-api Verified: 2026-09-24
- Together AI — 200+ open models, but the signup trial credit was retired; a $5 minimum purchase is required. Free limit: None — $5 minimum purchase to start. Credit card required. Status: deprecated. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#together-ai Verified: 2026-09-24
- Perplexity API (Sonar) — Search-grounded Sonar models are paid API only; the free consumer app is not API access. Free limit: None — Pro subscribers get $5/month of API credit. Credit card required. Status: deprecated. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#perplexity-api Verified: 2026-09-24
- Dahl Inference — Anonymous open-model inference on a decentralised GPU network — 100M tokens per key with no account, no card and no signup, on an OpenAI-compatible endpoint. Free limit: 100M tokens per API key. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#dahl-inference Verified: 2026-09-24
- LLM7.io — Gateway you can call with the literal placeholder key "unused" — no account, no email, no card, just a base URL and an OpenAI SDK. Free limit: 10 req/min anonymous; 40 req/min with a free token. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#llm7 Verified: 2026-09-24
- OVHcloud AI Endpoints — EU-hosted, GDPR-friendly inference over 20+ open-weight models at $0, usable without an API key on the anonymous tier. Free limit: Free — $0 per request on the anonymous tier. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#ovh-ai-endpoints Verified: 2026-09-24
- Hack Club AI — Free OpenAI-compatible access to Gemini, GPT-5.2, Kimi K2 and 30+ other models for Hack Clubbers — the most generous free tier aimed at teenage developers. Free limit: Free for Hack Club members. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#hack-club-ai Verified: 2026-09-24
- Space Bunny Alpha — Anonymous stealth model on OpenRouter with a 1M-token context window, free at $0 in and $0 out while the provider stays cloaked. Free limit: Free ($0/$0 per million tokens) while the preview runs. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#space-bunny-alpha Verified: 2026-09-24
- ZenMux — Unified gateway over 100+ models that keeps a small set of model ids permanently free, including DeepSeek V4 Flash Vision and GLM-5.3. Free limit: Free model ids, including deepseek/deepseek-v4-flash-vision-exp-free and z-ai/glm-5.3-free. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#zenmux-free Verified: 2026-09-24
- Puter.js — Client-side JavaScript SDK that gives a web app AI, storage, database and auth with no backend — the developer pays nothing because each signed-in user spends credits from their own Puter account. Free limit: Free for developers; end users spend their own Puter credits. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/llm-apis#puter-js Verified: 2026-09-24

### MCP Servers
Canonical page: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers
Entries: 64

- Filesystem — Secure local file operations with configurable allow-listed directories — the reference server every local agent starts with. Install: npx -y @modelcontextprotocol/server-filesystem /path/to/allowed/dir Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#filesystem-mcp Verified: 2026-09-24
- Fetch — Fetches a URL and converts it to clean markdown for the model, with robots.txt respect and chunked reading. Install: uvx mcp-server-fetch Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#fetch-mcp Verified: 2026-09-24
- Git — Read, search and diff a local git repository — history-aware agents without shelling out to raw git. Install: uvx mcp-server-git --repository /path/to/repo Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#git-mcp Verified: 2026-09-24
- Memory (Knowledge Graph) — Persistent knowledge-graph memory stored as local JSON — gives an agent recall across sessions for free. Install: npx -y @modelcontextprotocol/server-memory Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#memory-mcp Verified: 2026-09-24
- Sequential Thinking — Structured step-by-step reasoning with revision and branching — measurably improves multi-step agent plans. Install: npx -y @modelcontextprotocol/server-sequential-thinking Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#sequential-thinking-mcp Verified: 2026-09-24
- Time — Time and timezone conversion grounded in the host clock — stops agents hallucinating dates. Install: uvx mcp-server-time Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#time-mcp Verified: 2026-09-24
- Everything (Test Server) — Reference server exercising every MCP primitive — the fastest way to test a new client or transport. Install: npx -y @modelcontextprotocol/server-everything Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#everything-mcp Verified: 2026-09-24
- GitHub MCP Server — Repo automation, PRs, issues, code search and CI workflows — the most-starred MCP server in the ecosystem. Install: docker run -i --rm -e GITHUB_PERSONAL_ACCESS_TOKEN ghcr.io/github/github-mcp-server Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#github-mcp Verified: 2026-09-24
- Playwright MCP — Browser automation over accessibility snapshots rather than screenshots — deterministic agent browsing in Chromium, Firefox and WebKit. Install: npx -y @playwright/mcp@latest Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#playwright-mcp Verified: 2026-09-24
- Chrome DevTools MCP — Drives a real Chrome instance for performance traces, console errors and network inspection. Install: npx -y chrome-devtools-mcp@latest Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#chrome-devtools-mcp Verified: 2026-09-24
- Notion MCP — Reads and writes Notion pages and databases — the cleanest way to give an agent a knowledge base you already maintain. Install: npx -y @notionhq/notion-mcp-server Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#notion-mcp Verified: 2026-09-24
- Sentry MCP — Pulls issues, stack traces and traces into the prompt so an agent can triage production errors. Install: npx -y @sentry/mcp-server@latest Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#sentry-mcp Verified: 2026-09-24
- Supabase MCP — Postgres schema, migrations, edge functions and logs through one authenticated server. Install: npx -y @supabase/mcp-server-supabase@latest --read-only --project-ref=<ref> Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#supabase-mcp Verified: 2026-09-24
- MongoDB MCP — Query, aggregate and inspect collections, including Atlas administration. Install: npx -y mongodb-mcp-server --connectionString "<uri>" Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#mongodb-mcp Verified: 2026-09-24
- Redis MCP — Key-value access, data structure operations and vector set queries against Redis or Upstash. Install: npx -y @redis/mcp-redis Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#redis-mcp Verified: 2026-09-24
- Cloudflare MCP Servers — Fifteen-plus specialised servers for Workers, R2, D1, DNS, logs and Workers AI. Install: npx -y mcp-remote https://observability.mcp.cloudflare.com/mcp Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#cloudflare-mcp Verified: 2026-09-24
- Vercel MCP — Deployments, build logs, environment variables and project configuration. Install: npx -y mcp-remote https://mcp.vercel.com Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#vercel-mcp Verified: 2026-09-24
- AWS MCP Servers — Official suite covering S3, Lambda, DynamoDB, CloudWatch and 20+ other services. Install: uvx awslabs.core-mcp-server@latest Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#aws-mcp Verified: 2026-09-24
- Azure MCP Server — Natural-language management of Azure resources with Entra ID authentication. Install: npx -y @azure/mcp@latest server start Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#azure-mcp Verified: 2026-09-24
- Google Cloud MCP Servers — Managed MCP endpoints for Cloud Run, BigQuery, Spanner and gcloud workflows. Install: npx -y @google-cloud/gcloud-mcp Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#gcp-mcp Verified: 2026-09-24
- Docker MCP Gateway — Container management plus a gateway that catalogs and proxies hundreds of other MCP servers. Install: docker mcp gateway run Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#docker-mcp Verified: 2026-09-24
- Kubernetes MCP — kubectl-style cluster operations — inspect pods, apply manifests and read logs. Install: npx -y mcp-server-kubernetes Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#kubernetes-mcp Verified: 2026-09-24
- Terraform MCP — Provider and module registry lookups plus plan/apply assistance for infrastructure as code. Install: docker run -i --rm hashicorp/terraform-mcp-server Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#terraform-mcp Verified: 2026-09-24
- Grafana MCP — Query dashboards, Loki logs and Prometheus metrics from inside the agent loop. Install: docker run -i --rm mcp/grafana -t stdio Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#grafana-mcp Verified: 2026-09-24
- Elasticsearch MCP — Search indices and run aggregations; works against Elastic Cloud or self-hosted. Install: npx -y @elastic/mcp-server-elasticsearch Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#elasticsearch-mcp Verified: 2026-09-24
- Stripe MCP — Read customers, invoices and subscriptions, and create payment links from a prompt. Install: npx -y @stripe/mcp --tools=all --api-key=<rk_live_or_test> Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#stripe-mcp Verified: 2026-09-24
- Framelink Figma MCP — Pulls design tokens, layout and component structure out of Figma files into the editor, over stdio, using a personal access token. Install: npx -y figma-developer-mcp --figma-api-key=<token> Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#figma-mcp Verified: 2026-09-24
- Linear MCP — Create, search and update issues and projects in Linear from the agent loop. Install: npx -y mcp-remote https://mcp.linear.app/mcp Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#linear-mcp Verified: 2026-09-24
- Atlassian MCP — Jira issues and Confluence pages — the enterprise ticketing counterpart to Linear. Install: npx -y mcp-remote https://mcp.atlassian.com/v1/mcp Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#atlassian-mcp Verified: 2026-09-24
- Slack MCP — Read channels and post messages — the archived reference server's maintained successor. Install: npx -y @zencoderai/slack-mcp-server Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#slack-mcp Verified: 2026-09-24
- Airtable MCP — Read and write Airtable bases — a spreadsheet-shaped backend for agent prototypes. Install: npx -y mcp-remote https://mcp.airtable.com/mcp Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#airtable-mcp Verified: 2026-09-24
- Google Workspace MCP — Gmail, Drive, Calendar, Docs and Sheets through a single OAuth'd server. Install: uvx workspace-mcp Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#google-workspace-mcp Verified: 2026-09-24
- Zapier MCP — Bridges an agent to 8,000+ app actions without writing per-service integrations. Install: npx -y mcp-remote https://mcp.zapier.com/api/mcp/mcp Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#zapier-mcp Verified: 2026-09-24
- n8n MCP — Gives an agent the full n8n node catalogue so it can build and edit workflows. Install: npx -y n8n-mcp Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#n8n-mcp Verified: 2026-09-24
- Browserbase MCP — Cloud browser sessions with stealth mode, proxies and session replay for agents. Install: npx -y @browserbasehq/mcp-server-browserbase Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#browserbase-mcp Verified: 2026-09-24
- Apify Actors MCP — Runs any of Apify's 5,000+ scrapers as an agent tool, including the free-tier actors. Install: npx -y @apify/actors-mcp-server Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#apify-mcp Verified: 2026-09-24
- ElevenLabs MCP — Text-to-speech generation and voice management inside the agent loop. Install: uvx elevenlabs-mcp Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#elevenlabs-mcp Verified: 2026-09-24
- Hugging Face MCP — Searches models, datasets and Spaces, and can call Gradio apps as tools. Install: npx -y mcp-remote https://huggingface.co/mcp Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#huggingface-mcp Verified: 2026-09-24
- Qdrant MCP — Stores and retrieves memories in a Qdrant collection — vector memory as a tool, in about four lines of config. Install: uvx mcp-server-qdrant --qdrant-url <url> Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#qdrant-mcp Verified: 2026-09-24
- Chroma MCP — Local or cloud Chroma collections exposed as MCP tools for RAG and memory. Install: uvx chroma-mcp --client-type persistent --data-dir ./chroma Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#chroma-mcp Verified: 2026-09-24
- Neo4j MCP — Cypher queries and graph-schema inspection against AuraDB Free or self-hosted Neo4j. Install: uvx mcp-neo4j-cypher Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#neo4j-mcp Verified: 2026-09-24
- Postgres MCP Pro — Read-only-safe Postgres access with index tuning and health checks — the maintained replacement for the archived reference server. Install: uvx postgres-mcp --access-mode=restricted Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#postgres-mcp Verified: 2026-09-24
- SQLite MCP — Query and inspect a local SQLite file, including business-intelligence style summaries. Install: uvx mcp-server-sqlite --db-path ./data.db Status: degraded. Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#sqlite-mcp Verified: 2026-09-24
- MySQL MCP Server — Read-only-by-default MySQL queries and schema inspection. Install: uvx mysql-mcp-server Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#mysql-mcp Verified: 2026-09-24
- Context7 — Version-pinned, up-to-date documentation for thousands of libraries — the single highest-value server for coding agents. Install: npx -y @upstash/context7-mcp Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#context7-mcp Verified: 2026-09-24
- Firecrawl MCP — Crawls, scrapes and extracts structured data from sites, returning clean markdown for the model. Install: npx -y firecrawl-mcp Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#firecrawl-mcp Verified: 2026-09-24
- Exa MCP — Semantic web search tuned for agents, with deep-research and company-research modes. Install: npx -y exa-mcp-server Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#exa-mcp Verified: 2026-09-24
- Tavily MCP — Search, extract and map endpoints purpose-built for LLM grounding, with a genuinely usable free tier. Install: npx -y tavily-mcp@latest Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#tavily-mcp Verified: 2026-09-24
- Brave Search MCP — Independent web and local search index with a free API tier — no Google/Bing dependency. Install: npx -y @brave/brave-search-mcp-server Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#brave-search-mcp Verified: 2026-09-24
- DeepWiki MCP — Ask questions about any public GitHub repository and get answers grounded in its actual code and wiki. Install: npx -y mcp-remote https://mcp.deepwiki.com/mcp Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#deepwiki-mcp Verified: 2026-09-24
- Ref MCP — Token-efficient documentation search across technical sites, alternative to Context7. Install: npx -y ref-tools-mcp@latest Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#ref-tools-mcp Verified: 2026-09-24
- DuckDuckGo MCP — Keyless web search and safe text fetching — zero signup, which is rare in search tooling. Install: uvx duckduckgo-mcp-server Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#duckduckgo-mcp Verified: 2026-09-24
- Wikipedia MCP — Wikipedia search, article retrieval and section-level summaries. Install: uvx wikipedia-mcp Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#wikipedia-mcp Verified: 2026-09-24
- YouTube MCP — Fetches video transcripts by URL so agents can reason over talks and tutorials. Install: npx -y @anaisbetts/mcp-youtube Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#youtube-mcp Verified: 2026-09-24
- Obsidian MCP — Read and write notes in a local Obsidian vault — a personal knowledge base as agent memory. Install: npx -y obsidian-mcp /path/to/vault Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#obsidian-mcp Verified: 2026-09-24
- FastMCP — Pythonic framework and CLI for building MCP servers in about ten lines, with a built-in dev inspector. Install: uvx fastmcp run server.py Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#fastmcp Verified: 2026-09-24
- OpenAPI MCP Server — Turns any OpenAPI/Swagger spec into MCP tools — the fastest path to exposing an existing REST API. Install: npx -y @ivotoby/openapi-mcp-server --api-base-url <url> --openapi-spec <path> Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#openapi-mcp Verified: 2026-09-24
- AntV Chart MCP — Generates charts and dashboards (25+ chart types) as images from natural language data. Install: npx -y @antv/mcp-server-chart Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#antv-chart-mcp Verified: 2026-09-24
- Puppeteer (Archived) — The original browser-automation reference server. Superseded by Playwright MCP. Install: npx -y @modelcontextprotocol/server-puppeteer Status: deprecated. Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#puppeteer-mcp Verified: 2026-09-24
- Google Drive (Archived) — Searches and reads Google Drive files. Superseded by community Workspace servers. Install: npx -y @modelcontextprotocol/server-gdrive Status: deprecated. Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#google-drive-mcp Verified: 2026-09-24
- Slack (Archived Reference) — The original Slack channel-management reference server, now unmaintained. Install: npx -y @modelcontextprotocol/server-slack Status: deprecated. Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#slack-archived-mcp Verified: 2026-09-24
- Brave Search (Archived Reference) — Archived reference search server, replaced by Brave's own first-party server. Install: npx -y @modelcontextprotocol/server-brave-search Status: deprecated. Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#brave-search-archived-mcp Verified: 2026-09-24
- Wikidata MCP — Semantic and keyword search over Wikidata's ~30M entities and properties, so agents can resolve vague concepts into verifiable QIDs before writing SPARQL. Install: npx -y mcp-remote https://wd-mcp.wmcloud.org/mcp/ Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#wikidata-mcp Verified: 2026-09-24
- Figma MCP Server — Figma's own MCP server, hosted at mcp.figma.com over Streamable HTTP. Reads a selected frame's variables, components and layout into the editor, generates code from it, reuses real components through Code Connect and, while in beta, writes native content back to the canvas. Install: claude mcp add --transport http figma https://mcp.figma.com/mcp Anchor: https://devanimecx.github.io/free-ai-agent-stack/mcp-servers#figma-mcp-server Verified: 2026-09-24

### Agent Tools
Canonical page: https://devanimecx.github.io/free-ai-agent-stack/agent-tools
Entries: 82

- Cursor — AI-first code editor with whole-project awareness, tab completion and a multi-file agent. Free limit: Hobby plan: limited agent requests + 2,000 tab completions/month. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#cursor Verified: 2026-09-24
- Devin Desktop (formerly Windsurf) — Agentic editor from Cognition — the Windsurf/Cascade lineage, renamed after the 2026 acquisition. Free limit: Free plan: unlimited tab completion, quota-limited Cascade agent sessions. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#devin-desktop Verified: 2026-09-24
- GitHub Copilot Free — Copilot's genuinely free tier inside VS Code, JetBrains and the GitHub web editor. Free limit: 2,000 completions + 50 chat/agent requests per month. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#github-copilot Verified: 2026-09-24
- Zed — Rust-native, GPU-accelerated editor with a free built-in AI tier and bring-your-own-key support. Free limit: Free AI tier included; unlimited use with your own API keys. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#zed Verified: 2026-09-24
- Kiro — AWS's spec-driven agentic IDE — writes requirements and design docs before it writes code. Free limit: Free tier with monthly agentic-interaction quota. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#kiro Verified: 2026-09-24
- Trae — ByteDance's AI IDE with a free tier built around frontier models and an agent mode. Free limit: Free plan with monthly premium-model requests. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#trae Verified: 2026-09-24
- Amp (Sourcegraph) — Frontier agent from Sourcegraph with a free-forever plan, then pay-as-you-go with no subscription required. Free limit: Free plan with a monthly ad-supported allowance; BYOK option. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#amp Verified: 2026-09-24
- OpenCode — Open-source terminal coding agent with a client/server architecture and provider-agnostic model routing. Free limit: Free software — you bring a model key (free tiers work fine). No credit card required. Install: curl -fsSL https://opencode.ai/install | bash Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#opencode Verified: 2026-09-24
- Kilo Code — Open-source VS Code agent with a large free model allocation before you need your own key. Free limit: Free credits on signup for Anthropic/Gemini models; unlimited with BYOK. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#kilo-code Verified: 2026-09-24
- Gemini CLI — Google's open-source terminal agent with the most generous free quota of any first-party CLI. Free limit: 1,000 requests/day with a personal Google account (60 RPM). No credit card required. Install: npx -y @google/gemini-cli Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#gemini-cli Verified: 2026-09-24
- Qwen Code — Qwen's fork of Gemini CLI wired to Qwen3-Coder, with a large free daily request allowance via OAuth. Free limit: ~2,000 requests/day via Qwen OAuth. No credit card required. Install: npm install -g @qwen-code/qwen-code Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#qwen-code Verified: 2026-09-24
- Aider — Terminal pair-programmer that commits every change to git and maps your repo into the model's context. Free limit: Free software — works with any free LLM API key. No credit card required. Install: pip install aider-install && aider-install Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#aider Verified: 2026-09-24
- Cline — Autonomous coding agent for VS Code, JetBrains and the terminal, with human approval at every step. Free limit: Free and open source — bring any provider key (including free tiers). No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#cline Verified: 2026-09-24
- Roo Code — Cline fork with custom modes (architect, debugger, tester) and an orchestrator mode for multi-step work. Free limit: Free and open source — bring any provider key. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#roo-code Verified: 2026-09-24
- Continue — Open-source Copilot alternative for VS Code and JetBrains with customisable model routing. Free limit: Free software; connect Ollama for genuinely unlimited local use. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#continue-dev Verified: 2026-09-24
- OpenHands — Open-source software engineering agent (formerly OpenDevin) that runs in a sandboxed container. Free limit: Free software; hosted version has limited free credits. No credit card required. Install: docker run -it --rm -p 3000:3000 docker.all-hands.dev/all-hands-ai/openhands:latest Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#openhands Verified: 2026-09-24
- Goose — Block's local-first agent that can extend itself by writing its own MCP extensions. Free limit: Free and open source — bring any provider key. No credit card required. Install: curl -fsSL https://github.com/block/goose/releases/download/stable/download_cli.sh | bash Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#goose Verified: 2026-09-24
- Crush — Charm's glamorous terminal agent with MCP support, LSP awareness and session management. Free limit: Free and open source — bring any provider key. No credit card required. Install: brew install charmbracelet/tap/crush Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#crush Verified: 2026-09-24
- LangGraph — Stateful, graph-based agent orchestration with durable execution, human-in-the-loop and time travel. Free limit: Open source (MIT). LangGraph Platform has a free developer tier. No credit card required. Install: pip install -U langgraph Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#langgraph Verified: 2026-09-24
- LangChain — The widest integration ecosystem in the space — 600+ tools, loaders and vector store connectors. Free limit: Open source (MIT); no account required. No credit card required. Install: pip install -U langchain Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#langchain Verified: 2026-09-24
- LlamaIndex — Data framework for RAG: ingestion, chunking, indexing and query engines over your own documents. Free limit: Open source (MIT); LlamaCloud has a limited free tier. No credit card required. Install: pip install llama-index Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#llamaindex Verified: 2026-09-24
- CrewAI — Role-based multi-agent crews with delegation, sequential and hierarchical process modes. Free limit: Open source (MIT). No credit card required. Install: pip install crewai Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#crewai Verified: 2026-09-24
- AG2 (AutoGen) — Microsoft-originated multi-agent conversation framework: agents that talk to each other until the task is done. Free limit: Open source (Apache 2.0). No credit card required. Install: pip install ag2 Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#ag2-autogen Verified: 2026-09-24
- OpenAI Agents SDK — Small, provider-agnostic agent SDK: handoffs, guardrails, sessions and tracing in a few hundred lines. Free limit: Open source (MIT); works with any provider, not just OpenAI. No credit card required. Install: pip install openai-agents Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#openai-agents-sdk Verified: 2026-09-24
- Google Agent Development Kit — Google's agent framework with a built-in dev UI, evaluation harness and A2A protocol support. Free limit: Open source (Apache 2.0). No credit card required. Install: pip install google-adk Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#google-adk Verified: 2026-09-24
- Pydantic AI — Type-safe agent framework from the Pydantic team — validated structured outputs and dependency injection. Free limit: Open source (MIT). No credit card required. Install: pip install pydantic-ai Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#pydantic-ai Verified: 2026-09-24
- smolagents — Hugging Face's minimal agent library — code-writing agents in under 1,000 lines of core logic. Free limit: Open source (Apache 2.0). No credit card required. Install: pip install smolagents Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#smolagents Verified: 2026-09-24
- Agno — High-performance multi-modal agent framework with built-in memory, knowledge and reasoning tools. Free limit: Open source (MPL 2.0). No credit card required. Install: pip install agno Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#agno Verified: 2026-09-24
- DSPy — Programs language models instead of prompting them — optimisers compile prompts against a metric. Free limit: Open source (MIT). No credit card required. Install: pip install dspy Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#dspy Verified: 2026-09-24
- Haystack — Production RAG and agent pipelines from deepset, with strong evaluation and deployment tooling. Free limit: Open source (Apache 2.0). No credit card required. Install: pip install haystack-ai Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#haystack Verified: 2026-09-24
- Letta — Stateful agents with long-term memory that manage their own context window (formerly MemGPT). Free limit: Open source (Apache 2.0); free cloud sandbox available. No credit card required. Install: pip install letta Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#letta Verified: 2026-09-24
- Semantic Kernel — Microsoft's enterprise agent SDK for Python, .NET and Java with planners and process framework. Free limit: Open source (MIT). No credit card required. Install: pip install semantic-kernel Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#semantic-kernel Verified: 2026-09-24
- Mastra — TypeScript agent framework with workflows, evals, RAG and local dev playground. Free limit: Open source (Apache 2.0). No credit card required. Install: npm create mastra@latest Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#mastra Verified: 2026-09-24
- Vercel AI SDK — The standard TypeScript toolkit for streaming UI plus agents, with unified provider interfaces. Free limit: Open source (Apache 2.0). No credit card required. Install: npm install ai @ai-sdk/openai Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#vercel-ai-sdk Verified: 2026-09-24
- LiteLLM — One OpenAI-shaped interface over 100+ providers, with a proxy that adds budgets, keys and tracing. Free limit: Open source (MIT). No credit card required. Install: pip install litellm Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#litellm Verified: 2026-09-24
- n8n — Node-based automation with native AI agent nodes, MCP trigger and hundreds of integrations. Free limit: Self-hosted Community Edition is free forever (fair-code licence). No credit card required. Install: npx n8n Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#n8n Verified: 2026-09-24
- Dify — LLMOps platform for building chat agents, workflows and RAG apps with a visual editor and API output. Free limit: Self-hosted Community Edition free; cloud sandbox free tier. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#dify Verified: 2026-09-24
- Langflow — Visual drag-and-drop builder that compiles to LangChain-based flows and exposes each as an API. Free limit: Open source (MIT). No credit card required. Install: uvx langflow Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#langflow Verified: 2026-09-24
- Flowise — Low-code LLM orchestration with agent flows, tools and embeddable chat widgets. Free limit: Open source (Apache 2.0). No credit card required. Install: npx flowise start Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#flowise Verified: 2026-09-24
- Activepieces — Open-source Zapier alternative with AI pieces and MCP support, MIT-licensed rather than fair-code. Free limit: Self-hosted Community Edition free (MIT). No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#activepieces Verified: 2026-09-24
- MemPalace — Local-first memory for agents that stores conversations verbatim in ChromaDB and organises them into wings, halls and rooms instead of letting an LLM decide what is worth keeping. Free limit: Free — MIT licensed, runs locally with zero API calls. No credit card required. Install: pip install mempalace && mempalace init Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#mempalace Verified: 2026-09-24
- Cognee — Open-source memory platform that builds a self-hosted knowledge graph from your data, giving agents persistent long-term memory across sessions. Free limit: Free — self-hosted, runs with local extraction and embedding models. No credit card required. Install: pip install cognee Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#cognee Verified: 2026-09-24
- Mem0 — Drop-in memory layer for agents that extracts and stores salient facts between sessions, with the widest framework support of any memory library. Free limit: Free open-source self-host; hosted tier includes 10K memories. No credit card required. Install: pip install mem0ai Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#mem0 Verified: 2026-09-24
- Nanobrowser — Open-source Chrome extension that runs multi-agent web workflows — extract, compare and fill forms — inside your own browser, on your own keys. Free limit: Free — Apache-2.0 extension, works with any provider including Ollama and Groq. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#nanobrowser Verified: 2026-09-24
- Freebuff — Coding agent funded by terminal advertising — desktop, CLI, web and chat clients all backed by frontier models at no cost, in exchange for text ads. Free limit: Free with ad support; no subscription. No credit card required. Status: degraded. Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#freebuff Verified: 2026-09-24
- KISS Sorcar — Local-first agent framework that runs as a VS Code extension plus web and mobile clients, routing to any of hundreds of models across nine provider categories. Free limit: Free framework (Apache-2.0) — pay only your model provider. No credit card required. Install: pip install kiss-agent-framework Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#kiss-agent-framework Verified: 2026-09-24
- ReadyAgents Core — Self-hosted workflow engine and MCP toolkit that records agent runs so you can replay them offline, fork a run, diff two runs, or freeze one into a regression test. Free limit: Free — self-hosted, bring your own provider keys. No credit card required. Install: pip install readyagentsdev Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#readyagents-core Verified: 2026-09-24
- NanoBot — Deliberately tiny personal-agent framework from the HKU Data Intelligence lab that reimplements most of a large agent stack in roughly 4K lines. Free limit: Free — MIT licensed, bring your own provider keys. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#nanobot Verified: 2026-09-24
- Pincer — Self-hosted personal agent that lives in your messaging apps — WhatsApp, Telegram, Slack, Signal and email — with a large native tool set plus everything reachable over MCP. Free limit: Free — self-hosted via Docker, bring your own keys. No credit card required. Install: pip install pincer-agent && pincer init Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#pincer Verified: 2026-09-24
- QwenPaw — Personal assistant agent that runs fully locally against its own bundled QwenPaw-Flash models, so it needs no API key and no cloud account at all. Free limit: Free — local models included (2B/4B/9B). No credit card required. Install: pip install qwenpaw Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#qwenpaw Verified: 2026-09-24
- Tares — Self-hostable data plane for always-on agents: ingest events from Prometheus, OpenTelemetry and webhooks, then let an MCP server act on them. Free limit: Free — MIT licensed, runs on your own machine. No credit card required. Install: pip install tares Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#tares Verified: 2026-09-24
- Kitaru — Durable-execution runtime for Python agents from the ZenML team: record, replay and improve agent runs in production. Free limit: Free — Apache-2.0, self-hosted. No credit card required. Install: pip install kitaru Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#kitaru Verified: 2026-09-24
- Nexora — Self-hosted orchestration platform where agents get personas, skills and tools, with sub-agent delegation, RAG and semantic memory. Free limit: Free — MIT licensed self-hosted core. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#nexora Verified: 2026-09-24
- Automatos AI — Apache-2.0 multi-agent orchestration platform built around RAG and vector embeddings, able to route through free provider tiers including NVIDIA's. Free limit: Free — Apache-2.0, bring your own keys. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#automatos-ai Verified: 2026-09-24
- aigate — Single-compose self-hosted AI platform bundling inference, tool use, browser automation, image generation, speech synthesis, transcription and object storage. Free limit: Free — self-hosted; bundled providers have their own free tiers. No credit card required. Install: docker compose up Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#aigate Verified: 2026-09-24
- miii-cli — Offline coding agent for the terminal that runs entirely on Ollama, positioned as a local alternative to Claude Code, Cursor and Copilot. Free limit: Free forever — MIT licensed, no keys, no cloud. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#miii-cli Verified: 2026-09-24
- PawWork — Desktop agent for macOS and Windows with free models bundled in, aimed at office files, web search and scheduled automations rather than code. Free limit: Free — Apache-2.0, bundled models need no API key. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#pawwork Verified: 2026-09-24
- Code Buddy — Local-first coding agent that reads your repo, writes code and runs commands, with terminal, HTTP and optional desktop interfaces plus fleet collaboration. Free limit: Free — runs at $0 with Ollama; optional ChatGPT subscription integration. No credit card required. Install: npm install @phuetz/code-buddy Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#code-buddy Verified: 2026-09-24
- BrowserOS — Open-source agentic browser — a Chromium-based alternative to ChatGPT Atlas, Perplexity Comet and Dia, with agents built into the browser rather than bolted on. Free limit: Free — AGPL-3.0, bring your own model keys. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#browseros Verified: 2026-09-24
- UI-TARS Desktop — ByteDance's multimodal GUI agent stack that drives a real desktop — clicking, typing and navigating native apps — from screenshots and instructions. Free limit: Free — Apache-2.0, run the model locally or bring a key. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#ui-tars-desktop Verified: 2026-09-24
- Open Cowork — Desktop agent for Windows and macOS that installs Claude Code and MCP tooling in one click and runs the agent in a sandbox. Free limit: Free — MIT licensed, bring your own keys. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#open-cowork Verified: 2026-09-24
- Abu-Cowork — Local-first desktop agent with self-evolving skills and multi-model support, built as a privacy-preserving alternative to hosted coworking agents. Free limit: Free — open source, bring your own keys. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#abu-cowork Verified: 2026-09-24
- HyperDesk — Desktop coding workbench where the agent reads the project, runs commands, drives a browser and coordinates subagents — asking before it changes anything. Free limit: Free — open source, bring your own keys. No credit card required. Install: npm install hyperdesk Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#hyperdesk Verified: 2026-09-24
- Alice Memory — Local-first continuity layer that lets agents resume interrupted work, track open loops and recall decisions with provenance, exposed over MCP, HTTP and CLI. Free limit: Free — MIT licensed, local, no API keys. No credit card required. Install: uvx alice-memory mcp Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#alice-memory Verified: 2026-09-24
- Mazu — Coding-agent CLI with a memory and checkpoint layer: it keeps a queryable record of project decisions, conventions and past mistakes across sessions. Free limit: Free — open source, bring your own keys. No credit card required. Install: pip install mazu Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#mazu Verified: 2026-09-24
- pi-coding-agent — Minimal, inspectable coding agent that persists project facts to a plain .pi/memory.md file instead of a hidden database, with self-review and autonomous tool use. Free limit: Free — open source, multi-provider. No credit card required. Install: pip install pi-coding-agent Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#pi-coding-agent Verified: 2026-09-24
- mengram-ai — Human-like memory layer for agents with auto-save, auto-recall and a cognitive profile, split across semantic, episodic and procedural memory and exposed as MCP tools. Free limit: Free — open source, runs locally. No credit card required. Install: pip install mengram-ai Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#mengram-ai Verified: 2026-09-24
- haiku.rag — Agentic RAG that runs locally by default, using Ollama-hosted open models for the full pipeline — ingestion, embeddings, retrieval and generation. Free limit: Free — open source; the default pipeline needs no external API key. No credit card required. Install: pip install haiku.rag Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#haiku-rag Verified: 2026-09-24
- Pinakes — Portable, agent-first knowledge base where one directory holds the corpus, retrieved with SQLite FTS5 lexical search plus local embeddings and local reranking. Free limit: Free — no API key needed to search or re-index. No credit card required. Install: pip install pinakes Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#pinakes Verified: 2026-09-24
- Arc Rector — Agentic RAG stack assembled entirely from open-source components, with nine swappable layers so you can replace any piece without touching the rest. Free limit: Free — open source, no API keys, no vendor bills. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#arc-rector Verified: 2026-09-24
- local-rag-assistant — Chat with any codebase locally: AST-aware chunking, Ollama embeddings and a Chroma vector store, with no code leaving your machine. Free limit: Free — fully local, no API keys. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#local-rag-assistant Verified: 2026-09-24
- Pleias SLM RAG — On-device RAG API built on a ~300M-parameter model small enough to run on a Raspberry Pi 5, with no GPU and no external API calls. Free limit: Free — Apache-2.0 model weights. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#pleias-slm-rag Verified: 2026-09-24
- HOL Guard — Antivirus and runtime protection layer for agent tooling — plugins, skills and MCP servers — that sits between your agent and the code it is about to run. Free limit: Free — runs locally, no account. No credit card required. Install: pip install hol-guard Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#hol-guard Verified: 2026-09-24
- agent-bom — Scanner and self-hosted control plane for AI infrastructure — sweeps agent configs, MCP servers, instruction files, containers, cloud estate and model artefacts. Free limit: Free — open source, self-hosted. No credit card required. Install: pip install agent-bom Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#agent-bom Verified: 2026-09-24
- PanGuard — One-command monitoring and guarding for agents and MCP servers, aimed at catching what an agent does rather than what it was asked to do. Free limit: Free — MIT licensed, 100% open source. No credit card required. Install: npm install panguard Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#panguard Verified: 2026-09-24
- Bawbel Scanner — Security scanner for MCP servers and AI skill files that scores findings against OWASP's AIVSS rubric and ships an open vulnerability database with a public API. Free limit: Free — open source. No credit card required. Install: pip install bawbel-scanner Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#bawbel-scanner Verified: 2026-09-24
- Nightona — Community continuation of Daytona: elastic sandbox infrastructure for running AI-generated code and agent workflows in isolation. Free limit: Free — AGPL-3.0, self-hosted. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#nightona Verified: 2026-09-24
- Capka — Self-hosted sandbox for AI agents, built as a community alternative to hosted coworking sandboxes. Free limit: Free — open source, self-hosted. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#capka Verified: 2026-09-24
- coder-eval — Agent-agnostic framework for evaluating and benchmarking coding agents and skills, with support for comparing different agent harnesses head to head. Free limit: Free — open source. No credit card required. Install: pip install coder-eval Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#coder-eval Verified: 2026-09-24
- OpenMCP — Self-hosted benchmarking harness for computer-use agents acting through MCP, letting you measure tool-using agents reproducibly. Free limit: Free — open source, self-hosted. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#openmcp Verified: 2026-09-24
- agent-eval — Evaluation framework that auto-generates test tasks for an agent, executes them and scores results across several dimensions. Free limit: Free — open source. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#agent-eval Verified: 2026-09-24
- BenchClaw — Multi-dimensional agent evaluation that scores runs across ten dimensions and visualises the spread as radar charts. Free limit: Free — MIT licensed. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/agent-tools#benchclaw Verified: 2026-09-24

### Free Tiers
Canonical page: https://devanimecx.github.io/free-ai-agent-stack/free-tiers
Entries: 90

- Vercel — Static and serverless hosting with preview deployments per branch and AI Gateway included. Free limit: Hobby: 100GB bandwidth/mo, 100h serverless, $5/mo AI credit. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#vercel Verified: 2026-09-24
- Netlify — Static hosting, edge functions and form handling with per-branch deploy previews. Free limit: 100GB bandwidth/mo, 300 build minutes/mo. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#netlify Verified: 2026-09-24
- Cloudflare Pages — Unlimited-bandwidth static hosting that pairs with Workers, D1 and R2 on the same free account. Free limit: Unlimited requests and bandwidth; 500 builds/month. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#cloudflare-pages Verified: 2026-09-24
- Cloudflare Workers — V8-isolate serverless functions with cron triggers and durable objects, plus a free Workers AI binding. Free limit: 100,000 requests/day, 10ms CPU per request. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#cloudflare-workers Verified: 2026-09-24
- GitHub Pages — Static hosting straight from a repository, with a custom domain and HTTPS included. Free limit: 1GB site size, 100GB/mo soft bandwidth, 10 builds/hour. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#github-pages Verified: 2026-09-24
- Render — Container and web-service hosting with managed Postgres and cron jobs. Free limit: 750 instance-hours/mo; services spin down after 15 min idle. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#render Verified: 2026-09-24
- Railway — Fast deploys from a repo or Dockerfile with databases attached, billed by usage. Free limit: Trial credits on signup; $5/mo Hobby credit afterwards. Credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#railway Verified: 2026-09-24
- Fly.io — Runs Docker containers close to users with persistent volumes and private networking. Free limit: Limited free VM allowance for small machines (no managed databases). Credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#fly-io Verified: 2026-09-24
- Koyeb — Serverless container platform with a small always-on free instance and GPU options. Free limit: One free web service instance (0.1 vCPU / 512MB). No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#koyeb Verified: 2026-09-24
- Deno Deploy — Edge TypeScript runtime with KV storage, queues and cron built in — no build step. Free limit: 1M requests/mo, 100GB bandwidth/mo. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#deno-deploy Verified: 2026-09-24
- Oracle Cloud Always Free — The only genuinely free-forever VPS with usable specs — 2 Arm Ampere cores and 12GB RAM running 24/7, as one VM or split in two. Free limit: 2 ARM OCPUs + 12GB RAM, 200GB storage, 10TB egress/mo, forever. Credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#oracle-cloud-always-free Verified: 2026-09-24
- AWS Free Tier — Twelve months of t4g.small, Lambda allowances and 5GB S3, plus always-free Lambda and DynamoDB caps. Free limit: 12-month credits for new accounts; perpetual Lambda/DynamoDB allowances. Credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#aws-free-tier Verified: 2026-09-24
- Google Cloud Free Tier — e2-micro VM, Cloud Run and Firestore allowances, plus the $300 new-account credit. Free limit: Always-free e2-micro VM + Cloud Run/Speech/BigQuery monthly quotas. Credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#gcp-free-tier Verified: 2026-09-24
- Hugging Face Spaces — Free Docker or Gradio container hosting with a permanent public URL — 2 vCPU and 16GB RAM on the CPU Basic tier, enough for a real service rather than a toy demo. Free limit: 2 vCPU / 16GB RAM / 50GB ephemeral disk, unlimited Spaces. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#huggingface-spaces Verified: 2026-09-24
- Google Colab — Free hosted Jupyter with a T4 GPU — the cheapest path to fine-tuning or running a large model. Free limit: Free GPU sessions (T4), subject to availability and session limits. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#google-colab Verified: 2026-09-24
- Kaggle Notebooks — Free GPU/TPU notebooks with 30 hours of weekly GPU quota and persistent datasets. Free limit: 30 GPU hours/week (P100 or T4x2), 20 TPU hours/week. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#kaggle-notebooks Verified: 2026-09-24
- Modal — Serverless Python with GPU-per-second billing — good for embedding jobs and batch inference. Free limit: $30/month of included compute on the free plan. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#modal Verified: 2026-09-24
- E2B — Sandboxed cloud VMs built for agent code execution, with filesystem and process control. Free limit: $100 of sandbox credit on signup. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#e2b Verified: 2026-09-24
- Val Town — Write and deploy TypeScript functions in the browser with cron, SQLite and secrets included. Free limit: Free tier with 100K daily function runs. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#val-town Verified: 2026-09-24
- Supabase — Postgres with auth, storage, realtime and pgvector in one free project — the default agent backend. Free limit: 500MB database, 1GB file storage, 50K MAU auth. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#supabase Verified: 2026-09-24
- Neon — Serverless Postgres with copy-on-write branching — a database branch per feature or per agent run. Free limit: 0.5GB storage, 10 branches, 190 compute hours/mo. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#neon Verified: 2026-09-24
- Turso — Edge SQLite with embedded replicas — sub-millisecond reads next to your function, plus native vector search. Free limit: 5GB storage, 500M row reads/mo. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#turso Verified: 2026-09-24
- Cloudflare D1 — SQLite at the edge, bound directly to Workers with no connection pooling to manage. Free limit: 5GB storage, 5M rows read/day. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#cloudflare-d1 Verified: 2026-09-24
- CockroachDB Basic — Distributed SQL with automatic replication across regions and standard Postgres wire protocol. Free limit: 10GB storage, 50M request units/mo. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#cockroachdb-basic Verified: 2026-09-24
- MongoDB Atlas — Managed document database with a permanent M0 cluster, including Atlas Vector Search. Free limit: M0 cluster: 512MB storage, shared vCPU. Credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#mongodb-atlas Verified: 2026-09-24
- Firebase Firestore — Realtime document database with offline sync and client SDKs for every platform. Free limit: 1GiB storage, 50K document reads/day. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#firebase-firestore Verified: 2026-09-24
- Aiven — Managed Postgres, MySQL, Valkey and OpenSearch on a single always-free plan. Free limit: One 1GB managed service (Postgres, MySQL, Valkey or OpenSearch). No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#aiven-free Verified: 2026-09-24
- Convex — Reactive backend with TypeScript queries, mutations, scheduled functions and vector search. Free limit: 0.5GB storage, 1M function calls/mo. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#convex Verified: 2026-09-24
- Upstash Redis — Serverless Redis with per-request pricing and a REST API — no connection limit problems from serverless functions. Free limit: 500K commands/mo, 256MB. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#upstash-redis Verified: 2026-09-24
- PocketBase — Single-binary backend with SQLite, auth, file storage, realtime and an admin UI — self-host anywhere. Free limit: Unlimited (self-hosted, MIT). No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#pocketbase Verified: 2026-09-24
- Cloudflare R2 — S3-compatible object storage with zero egress fees — the reason to store agent artefacts here. Free limit: 10GB storage, 1M Class A ops/mo, free egress. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#cloudflare-r2 Verified: 2026-09-24
- Backblaze B2 — Cheap S3-compatible object storage with free egress through Cloudflare's bandwidth alliance. Free limit: 10GB storage, 1GB/day download free. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#backblaze-b2 Verified: 2026-09-24
- Qdrant Cloud — The best free vector tier: a real cluster with payload filtering, no card required. Free limit: 1GB cluster free forever (0.5 vCPU, 1GB RAM, 4GB disk). No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#qdrant-cloud Verified: 2026-09-24
- Pinecone Starter — Fully managed vector database with the least operational overhead of any option here. Free limit: 2GB storage, 2M write units and 1M read units/mo, 5 indexes. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#pinecone-starter Verified: 2026-09-24
- Weaviate Cloud — Open-source vector database with hybrid keyword+vector search and built-in vectoriser modules. Free limit: Free sandbox: 100K objects, 1GB memory, 1 collection. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#weaviate-cloud Verified: 2026-09-24
- Zilliz Cloud — Managed Milvus with strong performance at scale and a genuine free cluster. Free limit: Free tier: 5GB storage, 2.5M vector compute units/mo. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#zilliz-cloud Verified: 2026-09-24
- Upstash Vector — Serverless vector database over REST — no connection management, pairs with Upstash Redis on one key. Free limit: 10K vectors, 150K query units/day. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#upstash-vector Verified: 2026-09-24
- Chroma Cloud — Managed version of the most developer-friendly embedded vector store, with $5 of starter credit. Free limit: $5 starter credit; Chroma OSS remains free to self-host. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#chroma-cloud Verified: 2026-09-24
- Neo4j AuraDB Free — Managed graph database with native vector indexes — a knowledge graph and a vector store in one. Free limit: Free instance: 200K nodes, 400K relationships, no card required. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#neo4j-auradb Verified: 2026-09-24
- pgvector — Postgres extension that turns the database you already run into a vector store — no second system to operate. Free limit: Free (extension; self-hosted or on any Postgres free tier). No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#pgvector Verified: 2026-09-24
- LanceDB — Embedded vector database on the Lance columnar format — runs in-process, no server, no account. Free limit: Open source (Apache 2.0); $100 one-time cloud credit. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#lancedb Verified: 2026-09-24
- Clerk — Drop-in authentication with prebuilt UI components, organisations and webhooks. Free limit: 50,000 monthly retained users. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#clerk Verified: 2026-09-24
- WorkOS AuthKit — Auth with enterprise SSO, SCIM and directory sync built in from day one. Free limit: Free up to 1M monthly active users on AuthKit. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#workos-authkit Verified: 2026-09-24
- Auth0 — Mature identity platform with social logins, MFA and rules/extensibility. Free limit: 25,000 MAU on the free plan. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#auth0 Verified: 2026-09-24
- Logto — Open-source auth alternative to Auth0 with a clean developer experience and a free cloud tier. Free limit: 50,000 MAU on free cloud; self-hosted is unlimited. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#logto Verified: 2026-09-24
- Better Auth — TypeScript-first authentication library that lives inside your app — no third party in the request path. Free limit: Free (MIT, self-hosted in your own codebase). No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#better-auth Verified: 2026-09-24
- Keycloak — Red Hat's battle-tested identity server — full OIDC/SAML with self-hosting on a free VM. Free limit: Free (Apache 2.0, self-hosted). No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#keycloak Verified: 2026-09-24
- Upstash QStash — HTTP-based message queue and scheduler — the simplest way to add durable background jobs to serverless agents. Free limit: 1,000 messages/day. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#upstash-qstash Verified: 2026-09-24
- Inngest — Durable workflow engine with steps, retries and fan-out — long-running agents that survive restarts. Free limit: 50K executions/mo, 5 concurrent steps. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#inngest Verified: 2026-09-24
- Trigger.dev — Background jobs as code with long-running tasks, realtime progress and observability. Free limit: $5/mo of included compute. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#trigger-dev Verified: 2026-09-24
- Ably — Realtime pub/sub and presence for streaming agent output to a browser. Free limit: 6M messages/mo, 200 peak concurrent connections. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#ably Verified: 2026-09-24
- Pusher Channels — Managed WebSockets with channels, presence and client events. Free limit: 200K messages/day, 100 concurrent connections. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#pusher Verified: 2026-09-24
- Novu — Notification infrastructure that fans out one event to email, in-app, chat and push channels. Free limit: 30K events/mo on free cloud; self-hosted is unlimited. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#novu Verified: 2026-09-24
- CloudAMQP — Managed RabbitMQ on a small always-free instance — proper AMQP when QStash is not enough. Free limit: Little Lemur plan: 1M messages/mo, 20 connections. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#cloudamqp Verified: 2026-09-24
- Langfuse — Open-source LLM tracing, prompt management and evaluation — the default for debugging agent runs. Free limit: 50K observations/mo on free cloud; self-hosted is unlimited. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#langfuse Verified: 2026-09-24
- Helicone — One-line proxy that logs every LLM request with cost, latency and caching. Free limit: 10,000 requests/mo on free plan. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#helicone Verified: 2026-09-24
- Sentry — Error tracking with stack traces, releases, session replay and an official MCP server. Free limit: 5,000 errors/mo, 50 session replays, 1 user. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#sentry Verified: 2026-09-24
- Grafana Cloud — Metrics, logs and traces with a permanent free tier plus 14-day retention. Free limit: 10K metrics series, 50GB logs, 50GB traces, 3 users. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#grafana-cloud Verified: 2026-09-24
- Axiom — Log analytics built for high-cardinality events, with dashboards and alerts. Free limit: 0.5TB ingest/mo, 30-day retention. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#axiom Verified: 2026-09-24
- PostHog — Product analytics, session replay, feature flags and experiments in one SDK. Free limit: 1M events/mo, 5K replays, 1M feature-flag requests. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#posthog Verified: 2026-09-24
- Better Stack — Uptime monitoring, status pages, on-call alerting and log management. Free limit: 10 monitors at 3-min checks, 1 status page, 3GB logs. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#better-stack Verified: 2026-09-24
- UptimeRobot — Simple external uptime checks with Slack and email alerts — the guardrail for 'is my agent alive'. Free limit: 50 monitors at 5-minute intervals. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#uptimerobot Verified: 2026-09-24
- Plausible Analytics — Privacy-first, cookie-free web analytics — no consent banner needed, GDPR-compliant by design. Free limit: 30-day trial on cloud; self-hosted Community Edition is free forever. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#plausible Verified: 2026-09-24
- Umami — Lightweight, open-source, cookie-free analytics with a simple dashboard. Free limit: Free (MIT, self-hosted); managed cloud has a small free allowance. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#umami Verified: 2026-09-24
- Resend — Transactional email API with React Email templates and good deliverability. Free limit: 3,000 emails/mo, 100/day. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#resend Verified: 2026-09-24
- Brevo — Transactional email plus marketing campaigns and SMS on one generous free plan. Free limit: 300 emails/day (9,000/mo), unlimited contacts. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#brevo Verified: 2026-09-24
- Mailtrap — Email sandbox for testing plus a small sending allowance — stops agents spamming real inboxes in dev. Free limit: 1,000 emails/mo sending; free sandbox for testing. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#mailtrap Verified: 2026-09-24
- Algolia — Hosted search with typo tolerance, synonyms and instant-search UI libraries. Free limit: 10K search requests/mo, 1M records. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#algolia Verified: 2026-09-24
- DocSearch — Free Algolia-powered documentation search for open-source projects, including crawl and the search UI. Free limit: Free for open-source and developer documentation. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#docsearch Verified: 2026-09-24
- Typesense Cloud — Open-source (GPL) search engine with typo tolerance and vector search, self-hostable or managed. Free limit: Self-hosted is free; cloud offers trial clusters. No credit card required. Status: degraded. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#typesense-cloud Verified: 2026-09-24
- Actian VectorAI DB (Community Edition) — Embedded vector database from Actian that runs on a laptop with no service to deploy, built for agent memory and local RAG prototypes. Free limit: 5,000 vectors, free forever. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#actian-vectorai Verified: 2026-09-24
- Wikidata Vector Database — Wikimedia Deutschland's public vector database over Wikidata — roughly 30 million knowledge-graph entities exposed as embeddings for RAG grounding in verifiable, open data. Free limit: Free public access, no account. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#wikidata-vectordb Verified: 2026-09-24
- Opik — Comet's open-source LLM observability stack — tracing, evaluation, prompt management and production monitoring for agents and RAG pipelines. Free limit: Free — Apache-2.0, self-host the full platform. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#opik Verified: 2026-09-24
- free-llm-gateway — Self-hosted OpenAI-compatible gateway that fronts more than a dozen free LLM providers behind one endpoint and falls through to the next provider on failure. Free limit: Free — self-hosted, bring your own free provider keys. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#free-llm-gateway Verified: 2026-09-24
- ClawMetry — Real-time observability for a long list of agent runtimes — OpenClaw, NVIDIA NemoClaw, Claude Code, Codex, Cursor, Goose, opencode, Qwen Code, Aider and more — from one dashboard. Free limit: Free — open-source app, install locally. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#clawmetry Verified: 2026-09-24
- agent-observability — Local-first tracing for agents that records every tool call, error and dollar spent, and works with Claude, Cursor and any MCP-compatible agent. Free limit: Free forever — local, no account. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#agent-observability Verified: 2026-09-24
- claw-insights — Read-only observability sidecar that tails log files and CLI output, so you get agent tracing with no SDK, no code changes and no network calls. Free limit: Free — open source. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#claw-insights Verified: 2026-09-24
- OmniRoute — Self-hosted AI router that fans one endpoint out across hundreds of providers, with multiple routing strategies, compression and MCP/A2A support. Free limit: Free — open source, self-hosted; route to providers' free tiers. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#omniroute Verified: 2026-09-24
- agentgateway — Agentic proxy built on the MCP and A2A protocols, adding authentication, observability and governance in front of agents and MCP servers. Free limit: Free — open source, self-hosted. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#agentgateway Verified: 2026-09-24
- summoned-gateway — OpenAI-compatible gateway with routing, fallback, caching, guardrails and budget limits, with first-class support for Indian providers and INR cost tracking. Free limit: Free — self-hosted console, bring your own keys. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#summoned-gateway Verified: 2026-09-24
- fsrouter — Self-hosted gateway that puts one OpenAI-compatible endpoint in front of many providers, with automatic fallback, load balancing and key rotation. Free limit: Free — self-hosted. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#fsrouter Verified: 2026-09-24
- n9router — Self-hosted OpenAI-compatible routing gateway for dozens of providers, shipped as a Docker image and usable as a drop-in base URL for the major coding agents. Free limit: Free — self-hosted via Docker. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#n9router Verified: 2026-09-24
- Google AI Studio Starter Tier — No-card deployment path from AI Studio: prompt an app, click Publish, and get a live Cloud Run URL backed by Firestore or Cloud SQL plus Firebase Auth. Free limit: Two full-stack apps, no time limit, no billing account. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#google-ai-studio-starter Verified: 2026-09-24
- Hugging Face ZeroGPU — Shared on-demand GPU for Spaces, allocated per request rather than held for the lifetime of the Space — so a demo can use real GPU acceleration without paying hourly. Free limit: Free daily quota of GPU time, per-user. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#huggingface-zerogpu Verified: 2026-09-24
- Databricks Free Edition — A permanently free Databricks workspace for personal use — notebooks, SQL warehouse, the AI assistant, a GenAI playground and agent-builder tooling, with no cloud account. Free limit: Forever free, one serverless workspace with daily usage limits. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#databricks-free-edition Verified: 2026-09-24
- Toolforge — Wikimedia's shared cloud for community bots: web servers, scheduled jobs and managed access to Wikimedia data, free for anyone with a Wikimedia account. Free limit: Free web servers and job scheduling for Wikimedia tooling. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#toolforge Verified: 2026-09-24
- Zeabur — Deploy from a repository or a Dockerfile with services and databases wired together, on a free plan that needs no credit card. Free limit: Free plan — sign up and deploy, no card. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#zeabur Verified: 2026-09-24
- AMD Developer Cloud — Access to AMD Instinct MI300X GPUs with 192GB of HBM3 — enough to run 70B+ parameter models on a single instance without model parallelism — for ROCm and vLLM work. Free limit: $100 in credits for AMD AI Developer Program members. Credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#amd-developer-cloud Verified: 2026-09-24
- Yotta Shakti Studio — India-hosted serverless GPU platform with NVIDIA H100 and L40S instances billed per minute and scaling to zero, plus OpenAI-compatible AI endpoints and LoRA fine-tuning. Free limit: ₹10,000 in credits on signup (about $115). Credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#yotta-shakti-studio Verified: 2026-09-24
- GitHub Student Developer Pack — One verified student account that unlocks a bundle of cloud credits and services, including $200 of DigitalOcean credit, $100 of Azure credit, a free domain and Copilot. Free limit: Bundled credits and services for verified students. No credit card required. Anchor: https://devanimecx.github.io/free-ai-agent-stack/free-tiers#github-student-pack Verified: 2026-09-24

### Agent Skills
Canonical page: https://devanimecx.github.io/free-ai-agent-stack/skills
Entries: 78

- Anthropic Agent Skills — Anthropic's official skills repository — first-party packs that teach Claude Code and other agents house workflows: document handling, spreadsheet and slide authoring, PDF work and more. Install: npx skills add anthropics/skills Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#anthropics-skills Verified: 2026-09-24
- OpenAI Skills Catalog — OpenAI's curated Codex skills catalog — 39 maintained skills covering PDFs, GitHub CI repair, Playwright automation, deployment to Vercel, Cloudflare, Netlify and Render, Notion, Linear, Figma and security review. Superseded by openai/plugins, but still installable. Install: npx skills add openai/skills Status: deprecated. Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#openai-skills Verified: 2026-09-24
- Superpowers — An agentic skills framework and software-development methodology — a structured approach to planning, implementing and reviewing work with an agent, published as installable skills. Install: npx skills add obra/superpowers Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#superpowers Verified: 2026-09-24
- ClawHub — The skills and plugins registry for OpenClaw — 942 skills from verified publishers in the feed ClawHub publishes, sitting in front of a much larger open catalogue of community uploads. Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#clawhub Verified: 2026-09-24
- skills.sh — A web directory for agent skills with a CLI installer, built to make discovering and adding a skill a single command. Install: npx skills add vercel-labs/agent-skills Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#skills-sh Verified: 2026-09-24
- SkillsMP — An agent-skills marketplace indexing Codex and Claude skills, with browsing by creator and occupation. Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#skillsmp Verified: 2026-09-24
- Exa Agent Skills — Official skills for the Exa API — teaching an agent to call Exa's search and contents endpoints with cURL or raw HTTP when it already has URLs to read. Install: npx skills add exa-labs/agent-skills Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#exa-agent-skills Verified: 2026-09-24
- Neon Agent Skills — Official skills for operating Neon serverless Postgres from an agent — branch creation, connection handling and database workflow tasks. Install: npx skills add neondatabase/agent-skills Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#neon-agent-skills Verified: 2026-09-24
- Weaviate Agent Skills — Official skills covering vector search, semantic and hybrid retrieval, data import, RAG cookbook patterns, agentic RAG and multimodal PDF search. Install: npx skills add weaviate/agent-skills Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#weaviate-agent-skills Verified: 2026-09-24
- Apify Agent Skills — Official Apify skills for web scraping, data extraction and browser automation through Apify's actor platform. Install: npx skills add apify/agent-skills Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#apify-agent-skills Verified: 2026-09-24
- Microsoft Agent Skills — Microsoft's skills, plugins and custom-agent definitions for building on Azure SDKs and Microsoft Foundry — generated per service and language, alongside MCP-builder, documentation and workspace tooling. Install: npx skills add microsoft/skills Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#microsoft-agent-skills Verified: 2026-09-24
- Intellectronica Agent Skills — A maintained personal collection of agent skills, best known for a Notion REST API skill that drives workspaces with curl and jq rather than a vendor SDK. Install: npx skills add intellectronica/agent-skills Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#intellectronica-agent-skills Verified: 2026-09-24
- ASP.NET Core — Build, review, refactor, or architect ASP.NET Core web applications using current official guidance for .NET web development. Install: npx skills add openai/skills --skill aspnet-core Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#openai-aspnet-core Verified: 2026-09-24
- ChatGPT Apps — Build, scaffold, refactor, and troubleshoot ChatGPT Apps SDK applications that combine an MCP server and widget UI. Install: npx skills add openai/skills --skill chatgpt-apps Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#openai-chatgpt-apps Verified: 2026-09-24
- CLI Creator — Build a composable CLI for Codex from API docs, an OpenAPI spec, existing curl examples, an SDK, a web app, an admin tool, or a local script. Install: npx skills add openai/skills --skill cli-creator Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#openai-cli-creator Verified: 2026-09-24
- Cloudflare Deploy — Deploy applications and infrastructure to Cloudflare using Workers, Pages, and related platform services. Use when the user asks to deploy, host, publish, or set up a project on Cloudflare. Install: npx skills add openai/skills --skill cloudflare-deploy Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#openai-cloudflare-deploy Verified: 2026-09-24
- Define Goal — Helps the user state a concrete, measurable goal before work starts — invoked when someone asks to set an objective or create a goal. Install: npx skills add openai/skills --skill define-goal Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#openai-define-goal Verified: 2026-09-24
- Figma — Use the Figma MCP server to fetch design context, screenshots, variables, and assets from Figma, and to translate Figma nodes into production code. Install: npx skills add openai/skills --skill figma Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#openai-figma Verified: 2026-09-24
- Figma Code Connect — Connects Figma design components to code components using Code Connect mapping tools. Use when user says "code connect", "connect this component to code", "map this component", "link component to code", "create… Install: npx skills add openai/skills --skill figma-code-connect-components Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#openai-figma-code-connect-components Verified: 2026-09-24
- Figma Design System Rules — Generates custom design system rules for the user's codebase. Use when user says "create design system rules", "generate rules for my project", "set up design rules", "customize design system guidelines", or wa… Install: npx skills add openai/skills --skill figma-create-design-system-rules Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#openai-figma-create-design-system-rules Verified: 2026-09-24
- Figma Create File — Create a new blank Figma file. Use when the user wants to create a new Figma design or FigJam file, or when you need a new file before calling use_figma. Handles plan resolution via whoami if needed. Install: npx skills add openai/skills --skill figma-create-new-file Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#openai-figma-create-new-file Verified: 2026-09-24
- Figma Generate Design — Use this skill alongside figma-use when the task involves translating an application page, view, or multi-section layout into Figma. Install: npx skills add openai/skills --skill figma-generate-design Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#openai-figma-generate-design Verified: 2026-09-24
- Figma Generate Library — Build or update a professional-grade design system in Figma from a codebase. Use when the user wants to create variables/tokens, build component libraries, set up theming (light/dark modes), document foundation… Install: npx skills add openai/skills --skill figma-generate-library Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#openai-figma-generate-library Verified: 2026-09-24
- Figma Implement Design — Translates Figma designs into production-ready application code with 1:1 visual fidelity. Use when implementing UI code from Figma files, when user mentions "implement design", "generate code", "implement compo… Install: npx skills add openai/skills --skill figma-implement-design Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#openai-figma-implement-design Verified: 2026-09-24
- Figma Use — Mandatory prerequisite before any use_figma tool call — the Figma MCP workflow for pulling design context and translating nodes into code. Install: npx skills add openai/skills --skill figma-use Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#openai-figma-use Verified: 2026-09-24
- GitHub Address Comments — Help address review/issue comments on the open GitHub PR for the current branch using gh CLI; verify gh auth first and prompt the user to authenticate if not logged in. Install: npx skills add openai/skills --skill gh-address-comments Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#openai-gh-address-comments Verified: 2026-09-24
- GitHub Fix CI — Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions; use `gh` to inspect checks and logs, summarize failure context, draft a fix plan, and implement only after explicit appr… Install: npx skills add openai/skills --skill gh-fix-ci Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#openai-gh-fix-ci Verified: 2026-09-24
- Hatch Pet — Create, repair, validate, visually QA, and package Codex-compatible animated pets and pet spritesheets from character art, generated images, company or prospect brand cues, or visual references. Install: npx skills add openai/skills --skill hatch-pet Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#openai-hatch-pet Verified: 2026-09-24
- Jupyter Notebook — Use when user asks to create, scaffold, or edit Jupyter notebooks (`.ipynb`) for experiments, explorations, or tutorials; Install: npx skills add openai/skills --skill jupyter-notebook Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#openai-jupyter-notebook Verified: 2026-09-24
- Linear — Manage issues, projects & team workflows in Linear. Use when the user wants to read, create or updates tickets in Linear. Install: npx skills add openai/skills --skill linear Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#openai-linear Verified: 2026-09-24
- Migrate to Codex — Migrate supported instruction files, skills, agents, and MCP config into Codex project and global files. Install: npx skills add openai/skills --skill migrate-to-codex Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#openai-migrate-to-codex Verified: 2026-09-24
- Netlify Deploy — Deploy web projects to Netlify using the Netlify CLI (`npx netlify`). Use when the user asks to deploy, host, publish, or link a site/repo on Netlify, including preview and production deploys. Install: npx skills add openai/skills --skill netlify-deploy Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#openai-netlify-deploy Verified: 2026-09-24
- Notion Knowledge Capture — Capture conversations and decisions into structured Notion pages; use when turning chats/notes into wiki entries, how-tos, decisions, or FAQs with proper linking. Install: npx skills add openai/skills --skill notion-knowledge-capture Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#openai-notion-knowledge-capture Verified: 2026-09-24
- Notion Meeting Intelligence — Prepare meeting materials with Notion context and Codex research; use when gathering context, drafting agendas/pre-reads, and tailoring materials to attendees. Install: npx skills add openai/skills --skill notion-meeting-intelligence Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#openai-notion-meeting-intelligence Verified: 2026-09-24
- Notion Research Documentation — Research across Notion and synthesize into structured documentation; use when gathering info from multiple Notion sources to produce briefs, comparisons, or reports with citations. Install: npx skills add openai/skills --skill notion-research-documentation Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#openai-notion-research-documentation Verified: 2026-09-24
- Notion Spec to Implementation — Turn Notion specs into implementation plans, tasks, and progress tracking; use when implementing PRDs/feature specs and creating Notion plans + tasks from them. Install: npx skills add openai/skills --skill notion-spec-to-implementation Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#openai-notion-spec-to-implementation Verified: 2026-09-24
- OpenAI Docs — Answers questions about building with OpenAI products and APIs, Codex surfaces, and current official documentation. Install: npx skills add openai/skills --skill openai-docs Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#openai-openai-docs Verified: 2026-09-24
- PDF — Use when tasks involve reading, creating, or reviewing PDF files where rendering and layout matter; Install: npx skills add openai/skills --skill pdf Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#openai-pdf Verified: 2026-09-24
- Playwright — Use when task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via `playwright-cli` or the bundled wrapper script. Install: npx skills add openai/skills --skill playwright Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#openai-playwright Verified: 2026-09-24
- Playwright Interactive — Persistent browser and Electron interaction through `js_repl` for fast iterative UI debugging. Install: npx skills add openai/skills --skill playwright-interactive Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#openai-playwright-interactive Verified: 2026-09-24
- Render Deploy — Deploy applications to Render by analyzing codebases, generating render.yaml Blueprints, and providing Dashboard deeplinks. Install: npx skills add openai/skills --skill render-deploy Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#openai-render-deploy Verified: 2026-09-24
- Screenshot — Use when user explicitly asks for a desktop or system screenshot (full screen, specific app or window, or a pixel region), or when tool-specific capture capabilities are unavailable and an OS-level capture is n… Install: npx skills add openai/skills --skill screenshot Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#openai-screenshot Verified: 2026-09-24
- Security Best Practices — Perform language and framework specific security best-practice reviews and suggest improvements. Install: npx skills add openai/skills --skill security-best-practices Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#openai-security-best-practices Verified: 2026-09-24
- Security Ownership Map — Analyze git repositories to build a security ownership topology (people-to-file), compute bus factor and sensitive-code ownership, and export CSV/JSON for graph databases and visualization. Install: npx skills add openai/skills --skill security-ownership-map Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#openai-security-ownership-map Verified: 2026-09-24
- Security Threat Model — Repository-grounded threat modeling that enumerates trust boundaries, assets, attacker capabilities, abuse paths, and mitigations, and writes a concise Markdown threat model. Install: npx skills add openai/skills --skill security-threat-model Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#openai-security-threat-model Verified: 2026-09-24
- Sentry Issue Triage — Use when user asks to inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data via the Sentry CLI; perform read-only queries using the `sentry` command. Install: npx skills add openai/skills --skill sentry Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#openai-sentry Verified: 2026-09-24
- Speech — Use when user asks for text-to-speech narration or voiceover, accessibility reads, audio prompts, or batch speech generation via the OpenAI Audio API; Install: npx skills add openai/skills --skill speech Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#openai-speech Verified: 2026-09-24
- Transcribe — Transcribe audio files to text with optional diarization and known-speaker hints. Use when a user asks to transcribe speech from audio/video, extract text from recordings, or label speakers in interviews or mee… Install: npx skills add openai/skills --skill transcribe Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#openai-transcribe Verified: 2026-09-24
- Vercel Deploy — Deploy applications and websites to Vercel. Use when the user requests deployment actions like "deploy my app", "deploy and give me the link", "push this live", or "create a preview deployment". Install: npx skills add openai/skills --skill vercel-deploy Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#openai-vercel-deploy Verified: 2026-09-24
- WinUI App — Bootstrap, develop, and design modern WinUI 3 desktop applications with C# and the Windows App SDK using official Microsoft guidance, WinUI Gallery patterns, Windows App SDK samples, and CommunityToolkit compon… Install: npx skills add openai/skills --skill winui-app Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#openai-winui-app Verified: 2026-09-24
- Yeet (stage, commit, PR) — Stages, commits, pushes and opens a GitHub pull request in one flow with the GitHub CLI, only when explicitly asked. Install: npx skills add openai/skills --skill yeet Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#openai-yeet Verified: 2026-09-24
- Design Agent — CrewAI agent design and configuration — role, goal and backstory, LLM choice, tool assignment, max_iter/max_rpm/max_execution_time tuning, planning and code execution, delegation, knowledge sources, guardrails, and agents in YAML versus code. Install: npx skills add crewaiinc/skills --skill design-agent Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#crewai-design-agent Verified: 2026-09-24
- Design Task — CrewAI task design — writing descriptions and expected_output, chaining tasks with context, output formats (pydantic, JSON, file), guardrails for validation, human_input, async execution and markdown output. Install: npx skills add crewaiinc/skills --skill design-task Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#crewai-design-task Verified: 2026-09-24
- Getting Started — CrewAI architecture decisions and project scaffolding — choosing between LLM.call(), Agent.kickoff(), Crew.kickoff() and Flow, scaffolding with `crewai create flow`, YAML config, the @CrewBase crew.py pattern and conversational Flows. Install: npx skills add crewaiinc/skills --skill getting-started Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#crewai-getting-started Verified: 2026-09-24
- Ask Docs — A docs-aware assistant for CrewAI framework questions, answering from the current documentation rather than from model memory. Install: npx skills add crewaiinc/skills --skill ask-docs Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#crewai-ask-docs Verified: 2026-09-24
- Find Skills — Discovers and installs skills from the skills.sh registry from inside an agent session, so an agent can extend itself mid-task instead of the user installing files by hand. Install: npx skills add vercel-labs/skills --skill find-skills Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#vercel-find-skills Verified: 2026-09-24
- Dedalus Machines — Sets up and operates Dedalus Machines: a persistent Linux sandbox an agent can reach over SSH, run remote code in, or host a temporary service from, including CLI authentication and API base URL configuration. Install: npx skills add https://docs.dedaluslabs.ai/.well-known/skills/dedalus-machines/SKILL.md Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#dedalus-machines Verified: 2026-09-24
- PDF Generation — Generates PDFs from agent output, including layout and pagination, without leaving the session. Install: openclaw skills install @bartok9/pdf-generation Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#clawhub-pdf-generation Verified: 2026-09-24
- Skill Creator — Guides the creation of new skills — structure, metadata and the parts of a skill that change agent behaviour rather than just adding prose. Install: openclaw skills install @chindden/skill-creator Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#clawhub-skill-creator Verified: 2026-09-24
- Skill Vetter — Security-first vetting for a skill before it is installed: what a skill can reach, what it writes, and what it should not be trusted with. Install: openclaw skills install @spclaudehome/skill-vetter Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#clawhub-skill-vetter Verified: 2026-09-24
- OpenAI Whisper — Speech-to-text transcription driven through Whisper, wired up for an agent that receives audio. Install: openclaw skills install @steipete/openai-whisper Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#clawhub-openai-whisper Verified: 2026-09-24
- Skill Scanner — Scans a skill for known risky behaviour — static analysis across backdoors, cryptomining and data-exfiltration patterns. Install: openclaw skills install @sudhindrat/skill-security-scan Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#clawhub-skill-security-scan Verified: 2026-09-24
- Prompt Injection Defense — Hardens an agent session against prompt injection arriving through untrusted content: search results, email, downloaded files and PDFs. Install: openclaw skills install prompt-injection-defense Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#clawhub-prompt-injection-defense Verified: 2026-09-24
- Agent Guardrails — Implements guardrails for an agent — what it may do unattended and where it must stop and ask. Install: openclaw skills install @olmmlo-cmd/agent-guardrails Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#clawhub-agent-guardrails Verified: 2026-09-24
- Systematic Debugging — A staged debugging methodology: reproduce, isolate, hypothesise, then verify — instead of pattern-matching on the first plausible cause. Install: openclaw skills install @ivansslo/systematic-debugging Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#clawhub-systematic-debugging Verified: 2026-09-24
- Code Review — Reviews a diff the way a careful colleague does, separating correctness problems from style preferences. Install: openclaw skills install @wpank/code-review Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#clawhub-code-review Verified: 2026-09-24
- Refactoring — A deep refactoring workflow built on characterisation tests, small incremental steps, behaviour preservation and verification after each step. Install: openclaw skills install refactoring Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#clawhub-refactoring Verified: 2026-09-24
- Threat Modeling — Structured threat modelling with STRIDE, attack trees and risk scoring to find and prioritise threats in a system design. Install: openclaw skills install threat-modeling Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#clawhub-threat-modeling Verified: 2026-09-24
- OpenAI Plugins — OpenAI's current home for Codex skills and plugins — 62 plugin packages holding 536 skills, from first-party tooling to integrations published by Adobe, Atlassian, Canva, Cloudflare, Datadog, Figma, GitHub, Linear, Notion, Sentry, Stripe, Supabase, Vercel and more. Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#openai-plugins Verified: 2026-09-24
- CrewAI Skills — Official CrewAI skills for building multi-agent systems — agent and task design, project scaffolding, and a docs-aware helper for framework questions. Install: npx skills add crewaiinc/skills Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#crewai-skills Verified: 2026-09-24
- Vercel Agent Skills — Vercel's official skills for React and Next.js work and for shipping to Vercel: React best practices, composition patterns, view transitions, React Native, deployment, optimising cost and performance, plus web design and writing guidelines. Install: npx skills add vercel-labs/agent-skills Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#vercel-agent-skills Verified: 2026-09-24
- Browserbase Skills — Browserbase's official skills for reaching the web from an agent — search without a browser session, fetch a URL, drive a full browser, convert a browser flow into an API call, trace sessions, run adversarial UI tests and research a company. Install: npx skills add browserbase/skills Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#browserbase-skills Verified: 2026-09-24
- browse.sh — An open catalogue of browser-automation skills keyed by site: each entry names a domain, a skill and the method that reaches it, so an agent can ask what is already known about a site before writing a scraper from scratch. Install: npm i -g browse Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#browse-sh Verified: 2026-09-24
- Exa Contents — Calls the Exa Contents endpoint with cURL or raw HTTP when an agent already has URLs and needs page text, highlights, summaries, links, subpages or per-URL status without an SDK. Install: npx skills add exa-labs/agent-skills --skill exa-contents Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#exa-contents Verified: 2026-09-24
- Figma Agent Skills — Figma's own skill pack for working with design files through its MCP server — implementing designs as code, connecting components with Code Connect, generating design libraries and diagrams, and building Figma slides, FigJam boards, shaders and motion. Install: claude plugin install figma@claude-plugins-official Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#figma-skills Verified: 2026-09-24
- Alireza Rezvani Claude Skills — A large community skill library spanning engineering, marketing, product, compliance, finance and C-level advisory work — 388 skills plus custom agents, commands and references, installable across a dozen coding agents. Install: npx skills add alirezarezvani/claude-skills Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#alirezarezvani-claude-skills Verified: 2026-09-24
- A11y Audit — An accessibility audit pipeline over WCAG 2.2 Level A and AA: scan, fix and verify, with per-framework fix code and a compliance report. Covers React, Next.js, Vue, Angular, Svelte and plain HTML, and can run the checks in CI. Install: npx skills add alirezarezvani/claude-skills --skill a11y-audit Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#a11y-audit Verified: 2026-09-24
- Notion API — Drives a Notion workspace through the REST API with curl and jq rather than a vendor SDK or connector: query a database, create and update pages, and walk blocks, from any agent that can run shell commands. Install: npx skills add intellectronica/agent-skills --skill notion-api Anchor: https://devanimecx.github.io/free-ai-agent-stack/skills#notion-api Verified: 2026-09-24

## Licence and attribution

Data is CC-BY-4.0. Code is MIT. Reuse freely, including in AI answers, with
attribution to free-ai-agent-stack and, where practical, the entry's verified date.

Cite as: free-ai-agent-stack (2026). Adarsh Kushwah (Dev Animecx). https://devanimecx.github.io/free-ai-agent-stack