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.
AmrDabPipes a download into a shellllms.txtAmrDab/clawd-cursor/docs/llms.txt
clawdcursor > The local MCP server that gives any tool-calling agent safe control of the real > desktop — clicks, types, reads the screen, opens apps, drives any GUI. Local-only > (binds
neoneyeReads credentialsllms.txtneoneye/PlanExe/public/llms.txt
billing, and API key management. - No public REST API on this host. AI-facing MCP server: - https://mcp.planexe.org/mcp - https://mcp.planexe.org/mcp/ (for clients that require trailing slash) Agent discovery
AceDataCloudllms.txtAceDataCloud/Nexior/public/llms.txt
Documentation](https://docs.acedata.cloud): Comprehensive guides and API reference - [GitHub](https://github.com/AceDataCloud): Open source MCP servers and clients
Keesan12llms.txtKeesan12/martin-loop/llms-full.txt
compatible agent hosts use the MartinLoop workflow directly. Install: `npx -y @martinloop/mcp@latest` The MCP server uses local stdio transport for the public package. Through MCP, a host
mcpwarellms.txtmcpware/cross-code-organizer/llms.txt
Cross-Code Organizer (CCO) > Organize Claude Code memories, skills, MCP servers, commands, agents, rules, hooks, plans, sessions, and config across scopes. ## Docs - [AI Index](https://github.com/mcpware/cross-code-organizer/blob/main/AI_INDEX.md): Canonical AI-oriented
gizmodatallms.txtgizmodata/gizmosql/docs/llms.txt
docs.gizmosql.com/opentelemetry.md): traces and metrics export ## Integrations - [Extensions & Tools](https://docs.gizmosql.com/integrations.md): ecosystem integrations - [MCP Server](https://github.com/gizmodata/gizmosql-mcp): Model Context Protocol server and Claude Desktop extension so AI agents
CatCatUnclellms.txtCatCatUncle/openworkbuddy/llms.txt
creation. It supports bring-your-own LLM providers, local Claude Code/Codex engines, Markdown skills, MCP connectors, IM channels, local traces and an executable DAG canvas for short-drama assets. ## Best
openaccountantsllms.txtopenaccountants/openaccountants/llms-full.txt
/api/bundle/CA-ON` **Option 2 — Raw file URL:** Read individual skill files via raw.githubusercontent.com. **Option 3 — MCP server:** `https://www.openaccountants.com/api/mcp` — provides `list_skills`, `get_skill`, `get_skill_sections`, and structured
openaccountantsllms.txtopenaccountants/openaccountants/llms.txt
/api/bundle/CA-ON` **Option 2 — Raw file URL:** Read individual skill files via raw.githubusercontent.com. **Option 3 — MCP server:** `https://www.openaccountants.com/api/mcp` — provides `list_skills`, `get_skill`, `get_skill_sections`, and structured
oxbshwllms.txtoxbshw/watch-skill/llms.txt
Install the workspace: ```bash npx --yes @deepwatch/cli setup npx --yes @deepwatch/cli web --workspace ./my-project ``` MCP server configuration: ```json { "mcpServers": { "watch-skill": { "command": "uvx", "args": ["--from", "watch-skill[standard]", "watch-skill
griddynamicsPipes a download into a shellllms.txtgriddynamics/rosetta/llms-full.txt
upgrade = switch to latest. All releases uploaded to RAGFlow as separate datasets; MCP serves latest-stable only. Server-controlled VERSION (clients don't set it) → managed rollouts, no drift
daymoniollms.txtdaymonio/daymon/docs/llms-full.txt
fails (ideal for monitoring) - **never**: Never nudge How it works: 1. Task completes in MCP server or sidecar 2. Checks task's nudge_mode via `shouldNudgeTask()` 3. Checks quiet hours
daymoniollms.txtdaymonio/daymon/docs/llms.txt
shell) - **Sidecar** standalone Node.js HTTP server (cron scheduler, file watchers, task execution, embeddings) - **MCP Server** (stdio transport) for Claude Desktop and Claude Code integration - **Shared modules** used by both sidecar
brycewang-stanfordllms.txtbrycewang-stanford/StatsPAI/llms.txt
install statspai` (`pip install "statspai[fixest,plotting]"` for high-dimensional fixed effects and figures). MCP server: `statspai-mcp`. CLI: `statspai`. ## Start here - [AGENTS.md](AGENTS.md): how an agent discovers, calls
mediar-aillms.txtmediar-ai/mcp-server-macos-use/llms.txt
mcp-server-macos-use > MCP server for macOS desktop automation using native accessibility APIs ## Overview mcp-server-macos-use is a Model Context Protocol (MCP) server written in Swift that
NYTEMODEONLYllms.txtNYTEMODEONLY/polyterm/llms-full.txt
polyterm agent schemas --format json polyterm agent doctor --skip-network --format json polyterm agent mcp-server polyterm agent jsonl-server ``` All agent-facing tool calls return: ```json { "schema_version
NYTEMODEONLYllms.txtNYTEMODEONLY/polyterm/llms.txt
json` - Doctor: `polyterm agent doctor --skip-network --format json` - FastMCP stdio server: `polyterm agent mcp-server` - Legacy JSON-lines adapter: `polyterm agent jsonl-server` - Static manifest: `docs/tool-manifest.json` - Static schemas: `docs/schemas
mindroom-aiReads credentialsllms.txtmindroom-ai/mindroom/skills/mindroom-docs/references/llms-full.txt
connect to 100+ tools, including Gmail, Google Drive, Slack, Jira, Confluence, GitHub, and any MCP server ([Tools](https://docs.mindroom.chat/tools/), [MCP Servers](https://docs.mindroom.chat/mcp/)), and search knowledge bases built
mindroom-aillms.txtmindroom-ai/mindroom/skills/mindroom-docs/references/llms.txt
docs.mindroom.chat/deployment/bridges/) - [Telegram Bridge](https://docs.mindroom.chat/deployment/bridges/telegram/) - [Enable & Configure Tools](https://docs.mindroom.chat/tools/) - [MCP Servers](https://docs.mindroom.chat/mcp/) - [Dynamic Tools](https://docs.mindroom.chat/tools/dynamic-tools/) - [Minimal Agent Mode](https://docs.mindroom.chat/tools/agent-cli/) - [Background
ffrolivallms.txtffroliva/gflow-cli/llms.txt
gflow-cli > Python CLI and MCP server for Google Flow — drives Veo (image-to-video, text-to-video, reference-to-video) and Imagen (text-to-image) generations from the terminal
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.
