How real projects summarise themselves for language models.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
nirholasPipes a download into a shellllms.txtnirholas/three.ws/public/llms-full.txt
OpenAI Select Partner in the OpenAI Partner Network. Connect the free three.ws 3D Studio MCP server to ChatGPT and turn a prompt into an interactive, riggable, AR-ready 3D model
nirholasllms.txtnirholas/three.ws/public/llms.txt
authorization-server metadata. - [.well-known/chat-plugin.json](https://three.ws/.well-known/chat-plugin.json): ChatGPT-style plugin manifest. - [MCP server](https://three.ws/api/mcp): Hosted Model Context Protocol server (Streamable HTTP): avatars, glTF validation, agent data
billy-enrizkyReads credentialsllms.txtbilly-enrizky/openbrowser-ai/stress-tests/llms-full.txt
Ollama, and more - **Code Agent Mode** - Jupyter notebook-like code execution for complex automation - **MCP Server** - Model Context Protocol support for Claude Desktop integration - **Video Recording** - Record browser sessions
zapierllms.txtzapier/sdk/llms.txt
zapier/zapier-sdk-core`](https://www.npmjs.com/package/@zapier/zapier-sdk-core): shared core types. ## Optional - [Zapier MCP](https://github.com/zapier/zapier-mcp): the MCP-server alternative for tool-calling from Cursor, Claude Desktop, or Codex. Reach for it when
mattrobinsonsrePipes a download into a shellllms.txtmattrobinsonsre/terrapod/llms.txt
Baked into the api + runner images and published standalone. | Go | | `mcp/` | `terrapod-mcp` — official **MCP server**: a local stdio adapter letting an AI agent (Claude, Cursor, …) drive one Terrapod instance
saelounllms.txtsaeloun/miru-web/public/llms-full.txt
OpenAPI: https://app.miru.so/openapi.json - API catalog: https://app.miru.so/.well-known/api-catalog - MCP endpoint: https://app.miru.so/mcp - MCP Server Card: https://app.miru.so/.well-known/mcp/server-card.json - Agent skills: https://app.miru.so/.well-known/agent-skills/index.json - Public product docs: https://miru.so
saelounllms.txtsaeloun/miru-web/public/llms.txt
OpenAPI: https://app.miru.so/openapi.json - API catalog: https://app.miru.so/.well-known/api-catalog - MCP endpoint: https://app.miru.so/mcp - MCP Server Card: https://app.miru.so/.well-known/mcp/server-card.json - Agent skills: https://app.miru.so/.well-known/agent-skills/index.json - Marketing/docs: https://miru.so/docs
sachitrafallms.txtsachitrafa/YourMemory/llms.txt
entity extraction) - **Protocol:** MCP (Model Context Protocol) stdio server - **API:** FastAPI HTTP server on port 3033 ## MCP Tools - `recall_memory(query, user_id, current_path?)` — hybrid retrieval with graph expansion
kreuzberg-devReads credentialsllms.txtkreuzberg-dev/liter-llm/llms.txt
openai/*", "anthropic/*"] rpm = 60 budget = 50.0 [[providers]] name = "openai" api_key = "${OPENAI_API_KEY}" ## MCP Server Model Context Protocol server with 22 tools matching the REST API. Supports stdio
QVerisAIPipes a download into a shellllms.txtQVerisAI/QVerisAI/agent/llms-full.txt
only the latest Discover ID, endpoint, query, and result summaries for 30 minutes. The MCP server preserves process/session correlation but does not provide semantic route memory. JavaScript and Python
QVerisAIPipes a download into a shellllms.txtQVerisAI/QVerisAI/agent/llms.txt
qverisai/cli — no upfront catalog schemas, deterministic output, API discovery without preloading the catalog - MCP Server v0.15.0 (local stdio fallback): npx @qverisai/mcp — for stdio-only IDE integrations - JavaScript SDK v0.10.0
dengyierllms.txtdengyier/OpenWorkProof/llms.txt
mcp`. The MCP client manages this process. There is no hosted remote endpoint or API key in this setup. `owp` is the separate CLI, not the stdio server. The optional
Mistgatellms.txtMistgate/mistgate/llms.txt
node over SSH](https://mistgate.app/getting-started/ssh-install/) - [Add a node manually](https://mistgate.app/getting-started/add-node/) - [MCP server and tool contracts](https://mistgate.app/reference/mcp/) - [API reference](https://mistgate.app/reference/api/) - [Updates](https://mistgate.app/operations/updates/)
SentryReads credentialsllms.txtgetsentry/dotagents/docs/public/llms.txt
dotagents > Shared tooling for coding agents dotagents manages agent skills, MCP servers, hooks, subagents, and plugins declared in `agents.toml`, and handles symlinks and config generation so tools like Claude Code
vinkius-labsReads credentialsllms.txtvinkius-labs/mcp-fusion/docs/llms.txt
MCP Fusion > fusion is the TypeScript framework for production MCP servers. MVA architecture, structured perception for AI agents — zero hallucination, zero data leaks. ## What is MCP Fusion? MCP Fusion
YOLOW92llms.txtYOLOW92/pagesift/llms.txt
hosted Rust binary with a CLI, Firecrawl v1/v2 and Jina Reader HTTP APIs, an MCP server, and Python and Node.js packages. AGPL-3.0 or commercial license. - Input: URLs (HTTP
KyaniteLabsllms.txtKyaniteLabs/kinocut/docs/llms-full.txt
separate website publication check. ## Identity and release truth Kinocut is an Apache-2.0 MCP server, Python client and CLI for guarded media workflows. KyaniteLabs publishes it. The CLI is kino
KyaniteLabsllms.txtKyaniteLabs/kinocut/llms.txt
Kinocut > Guardrailed video editing MCP server, Python library, and CLI for AI agents. > Local-first. Apache-2.0. Formerly mcp-video. ## One-line definition Kinocut is an Apache-2.0 open-source
clearcotelabsllms.txtclearcotelabs/clearcote-browser/llms.txt
with `--shm-size=1g -p 127.0.0.1:9222:9222 --security-opt seccomp= `; see /docker/README.md. - MCP server: `clearcote-mcp` (PyPI / npm). Profile Manager desktop app 0.12.2 (Windows + Linux): https://github.com/clearcotelabs/clearcote-profile-manager ## Quick
erikdarlingdatallms.txterikdarlingdata/PerformanceStudio/llms.txt
mismatches, missing indexes, spills, parallel skew, parameter sniffing, implicit conversions, and more. Built-in MCP server for AI-assisted plan analysis. SSMS extension for one-click plan transfer. Runs
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.
