How real projects summarise themselves for language models.
garrytanllms.txtgarrytan/gstack/gstack/llms.txt
this coding agent: install the CLI, initialize a local PGLite or Supabase brain, register MCP, capture per-remote trust policy. - [/ship](ship/SKILL.md): Ship workflow: detect + merge base branch, run tests
koala73llms.txtkoala73/worldmonitor/public/llms-full.txt
layers, a plain LLM is cheaper and faster. **How an agent should call it:** - **MCP server (recommended):** `https://worldmonitor.app/mcp` — Streamable HTTP; issue `tools/list` for the live inventory. Auth: OAuth2
koala73llms.txtkoala73/worldmonitor/public/llms.txt
layers, a plain LLM is cheaper and faster. **How an agent should call it:** - [MCP server (recommended)](https://worldmonitor.app/mcp): Streamable HTTP; issue `tools/list` for the live inventory. Auth: OAuth2
Microsoftllms.txtmicrosoft/ai-agents-for-beginners/15-browser-use/llms.txt
# Check Balance Source: https://docs.browser-use.com/api-reference/accounts/check-balance https://api.browser-use.com/api/v1/openapi.json get /balance Returns the user
headroomlabs-aillms.txtheadroomlabs-ai/headroom/llms.txt
before they reach the model. Same answers, 60–95% fewer tokens. Library, proxy, and MCP server. Apache 2.0, local-first. Headroom is shipped as a Python package (`headroom
mem0aillms.txtmem0ai/mem0/docs/llms.txt
evaluation key in <5 seconds. Use it immediately against the Platform API or MCP server. When the human is ready, claim with `mem0 init --email ` to transfer ownership (memories preserved
DeusDatallms.txtDeusData/codebase-memory-mcp/docs/llms.txt
codebase-memory-mcp > An open-source Model Context Protocol (MCP) server that indexes a codebase into a persistent knowledge graph of functions, classes, call chains, HTTP routes, and cross-service
OpenAIllms.txtopenai/openai-agents-python/docs/llms-full.txt
tool contexts, and test tool execution paths. - [Model Context Protocol](https://openai.github.io/openai-agents-python/mcp/): Integrate MCP servers so agents can dynamically request data or actions from external providers via a standard
OpenAIllms.txtopenai/openai-agents-python/docs/llms.txt
manage schemas, and work with tool contexts. - [Model Context Protocol](https://openai.github.io/openai-agents-python/mcp/): Connect MCP servers so agents can request external data or actions through standardized tool APIs. ## Operations
alirezarezvanillms.txtalirezarezvani/claude-skills/docs/llms-full.txt
sync scripts in `scripts/`. Supported targets include: - **Claude Code** (primary) — plugins, agents, slash commands, MCP servers, hooks - **OpenAI Codex** — `scripts/sync-codex-skills.py`, `~/.codex/` - **Gemini CLI** — `scripts/sync-gemini-skills.py` - **Cursor** — rules-format export - **Hermes Agent
Evil0ctalllms.txtEvil0ctal/Douyin_TikTok_Download_API/llms.txt
Douyin (抖音) and TikTok. One `docker compose up` > gives you a REST API, an MCP server and a web console, backed by an identity > pool (cookies + proxies + fingerprints) that mints
tonhowtfllms.txttonhowtf/omniget/llms-full.txt
github.com/tonhowtf/omniget#the-browser-extension-step-by-step) - [The Tools section: 156 tools in 24 categories](https://github.com/tonhowtf/omniget#the-tools-section-156-tools-in-24-categories) - [MCP server for Claude Code, Cursor and VS Code, and a Claude Code plugin](https://github.com/tonhowtf/omniget#omniget-for-ai-agents-mcp-server-and-claude-code-plugin)
tonhowtfllms.txttonhowtf/omniget/llms.txt
permissions, undo, durable jobs, loops that repeat until a test command passes, an embedded MCP server with 49 tools, and an isometric house called the World where the agents
corsairdevllms.txtcorsairdev/corsair/docs/llms.txt
docs.corsair.dev/mcp-adapters/claude-sdk.md): Use Corsair with the Claude Agent SDK via an in-process MCP server. - [Vercel AI SDK](https://docs.corsair.dev/mcp-adapters/vercel-ai.md): Connect Corsair to the Vercel AI SDK over HTTP
A markdown file at a website's root that gives language models a short guide to the site and links to the pages worth reading.
The same idea with the content included, so an agent can read the documentation in one request.
Agents and tools that fetch documentation on someone's behalf. It's a proposal, not a standard, and support varies.
Start with a one-line summary, then sections of links with a sentence each. The examples here show what real projects do.
