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.
AVIDS2Reads credentialsllms.txtAVIDS2/memorix/llms.txt
memorix setup --list` lists supported agent entry points. - `memorix serve` starts the manual stdio MCP server for IDEs and agents. - `memorix background start` starts the HTTP MCP service and dashboard
fluffyponyPipes a download into a shellllms.txtfluffypony/dothething/llms.txt
email notifications on task completion, live input injection during execution, and a browser MCP server (dtt --browsermcp) that exposes the SearXNG + Notte stack to other agents over stdio
unbrowse-aiReads credentialsllms.txtunbrowse-ai/unbrowse/llms.txt
would write; `setup --remove` undoes it. Restart the agent (or reload its skills and MCP servers) so the new skill and tools load. - **Sandboxed agent** (a cloud container with restricted
CodeAbrallms.txtCodeAbra/iai-personal-memory-engine/llms.txt
query`, `episodes_recent`, `curiosity_pending`. Optional and off by default: a separate `iai-tools` MCP server (code index, session-event store, command executor), enabled with `iai-mcp capture-hooks install
cryxnetReads credentialsllms.txtcryxnet/DeepMCPAgent/llms-full.txt
agentic AI systems: agents > (`build_agent()`), the tools they call (`@tool` functions and MCP servers built > with the MCP server SDK or generated from an OpenAPI spec with MCPcast
cryxnetReads credentialsllms.txtcryxnet/DeepMCPAgent/llms.txt
agentic AI systems: agents > (`build_agent()`), the tools they call (`@tool` functions and MCP servers built > with the MCP server SDK or generated from an OpenAPI spec with MCPcast
alisaittekeReads credentialsllms.txtalisaitteke/photoshop-mcp/llms.txt
photoshop-mcp > MCP server for Adobe Photoshop — 1.7.18 — 122 tools (generative AI + 16 recipes), standalone web UI, and state-aware agent workflows. Unofficial; not affiliated with Adobe. **Website:** https://photoshop-mcp.com
riponcmllms.txtriponcm/projectmem/llms.txt
events in plain text, feeds that history back to the agent through a native > MCP server, and warns at git commit time before you repeat an approach that > already failed
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
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
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
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
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
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-aiReads credentialsllms.txtHelpCode-ai/anythingmcp/llms-full.txt
your company runs and to the documents on your file servers, without writing an MCP server. **One question in Claude, answered from Etsy, SAP and a logistics API.** https://github.com
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
aeonfunllms.txtaeonfun/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
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
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
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
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.
