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.
santiferllms.txtsantifer/cv-santiago/public/llms.txt
Introduction to Model Context Protocol - **Anthropic (2026):** Claude Code in Action - **Anthropic (2026):** Advanced MCP Topics - **Anthropic (2026):** Building with the Claude API - **Anthropic (2026):** AI Fluency: Framework & Foundations — Anthropic
GrafeoDBllms.txtGrafeoDB/grafeo/docs/llms.txt
/GrafeoDB/grafeo-langchain)** - LangChain integration - **[grafeo-llamaindex](https://github.com/GrafeoDB/grafeo-llamaindex)** - LlamaIndex integration - **[grafeo-mcp](https://github.com/GrafeoDB/grafeo-mcp)** - Model Context Protocol server - **[grafeo-memory](https://github.com/GrafeoDB/grafeo-memory)** - AI memory layer for LLM applications
Marve10sllms.txtMarve10s/Better-Fullstack/llms.txt
ships as the `create-better-fullstack` CLI, a browser Stack Builder, and an MCP server for coding agents. Use it instead of hand-writing starter files. This file
aayushchllms.txtaayushch/laya/landing/llms.txt
show related documents, Coherence traces include them, and list/search/read document tools are exposed over MCP - **Context Association**: Automatic semantic grouping of related cards across platforms; learns editable natural-language context
krakenfxPipes a download into a shellllms.txtkrakenfx/kraken-cli/llms.txt
derivatives on Kraken with structured JSON output. One install puts `kraken`, `kraken-mcp` (the MCP server) and `kraken-shell` on your PATH. ## Start Here - [CONTEXT.md](https://raw.githubusercontent.com/krakenfx/kraken-cli/main/CONTEXT.md): Runtime context
aaronjmarsllms.txtaaronjmars/aeon/llms.txt
Actions. Once it exists, drive it from ChatGPT, Claude or Cursor through the hosted MCP server at https://www.aeon.fun/connect/mcp. Repo: https://github.com/aeonfun/aeon Site: https://www.aeon.fun ## Core entry points
AnxForeverllms.txtAnxForever/stylekit/public/llms.txt
current CLI. For an MCP client, add this once to its MCP server configuration: ```json { "mcpServers": { "stylekit": { "command": "npx", "args": ["-y", "--prefer-online", "stylekit-mcp@latest"] } } } ``` The CLI checks
astashovllms.txtastashov/liftosaur/llms.txt
Android), the Apple Watch app, REST API keys, and the account tools of the MCP server. The web editor's weekly sets per muscle group are free. - Premium plans: monthly
ronak-createllms.txtronak-create/FableCut/docs/llms.txt
local folder; nothing is uploaded to a cloud service. - Control surfaces: an MCP server (stdio, client-neutral), a REST API, and direct edits to `project.json` with live reload over server
HelpCode-aillms.txtHelpCode-ai/anythingmcp/llms.txt
MCP Gateway](https://raw.githubusercontent.com/HelpCode-ai/anythingmcp/main/docs/connectors/mcp-bridge.md): The MCP Bridge connector lets you connect to other MCP servers and re-expose their tools through AnythingMCP. - [OData to MCP](https://raw.githubusercontent.com/HelpCode-ai/anythingmcp/main/docs/connectors/odata.md): AnythingMCP
AbilityaiPipes a download into a shellllms.txtAbilityai/trinity/llms.txt
Control plane: Vue frontend (:80), FastAPI backend (:8000, OpenAPI at `/docs`), MCP server (:8080/mcp), scheduler, Redis, PostgreSQL - on a network the agents cannot reach. Each agent is a container
RareSensellms.txtRareSense/Nova3D/mcp/llms.txt
NOVA3D_TOKEN` if you cannot complete the browser flow. Important: after installing the MCP server in any client, the next step is to call `nova3d_login` or `nova3d_setup` from
buzzer-rellms.txtbuzzer-re/Rikugan/llms.txt
logged with a reverse operation. `/undo [N]` replays them in reverse. - **MCP**: External MCP servers configured via `mcp.json`. Tools bridged into the registry with `mcp_ _ ` prefix. - **Providers**: Anthropic (Claude), OpenAI
buzzer-rellms.txtbuzzer-re/Rikugan/webpage/llms.txt
running. Scripts are limited to the disassembler's scripting API. - **MCP Client**: Connects external MCP servers via stdio + JSON-RPC 2.0 with Content-Length framing. Heartbeat monitoring detects dead servers
genomoncologyllms.txtgenomoncology/biomcp/docs/llms-full.txt
/reference/error-codes/): Reference details for Error Codes. - [FAQ](https://biomcp.org/reference/faq/): Reference details for FAQ. - [MCP Server Reference](https://biomcp.org/reference/mcp-server/): Reference details for MCP Server Reference. - [Quick Reference](https://biomcp.org
genomoncologyPipes a download into a shellllms.txtgenomoncology/biomcp/docs/llms.txt
BioMCP BioMCP is a biomedical CLI and MCP server for searching biomedical data sources. ## Get started Install BioMCP: curl -fsSL https://biomcp.org/install.sh | bash Read the [installation guide](https://biomcp.org
nubenetesllms.txtnubenetes/awesome-kubernetes/v2-docs/llms.txt
microservices engines like Spring Boot, Quarkus, and Micronaut. Essential for legacy modernization... - [Awesome MCP Servers](https://github.com/punkpeye/awesome-mcp-servers): Curator Insight: A community-curated collection of servers implementing the Model Context
decionisllms.txtdecionis/agent-safe-pipeline/llms-full.txt
authority as session.subject for writes): https://github.com/decionis/agent-safe-pipeline/blob/master/docs/gateway/subject-sessions.md - MCP tool profiles (agent-safe.profile.mcp/1: an MCP server's consequential tools as data, each with its action, target template, subject argument, consequential
decionisllms.txtdecionis/agent-safe-pipeline/llms.txt
authority as session.subject for writes): https://github.com/decionis/agent-safe-pipeline/blob/master/docs/gateway/subject-sessions.md - MCP tool profiles (agent-safe.profile.mcp/1: an MCP server's consequential tools as data, each with its action, target template, subject argument, consequential
neondatabasellms.txtneondatabase/mcp-server-neon/public/llms.txt
Neon MCP Server > Connect AI tools to Lakebase Postgres databases on Neon using the Model Context Protocol (MCP). The Neon MCP Server enables Large Language Models to manage Lakebase Postgres
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.
