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.
alexei-ledllms.txtalexei-led/cloud-mcp-server/llms.txt
MCP Server > MCP server that provides AI assistants with access to AWS CLI, enabling natural language interaction with AWS services through the Model Context Protocol. AWS MCP Server implements
Cassette-Editorllms.txtCassette-Editor/oh-my-cassette/llms.txt
Cassette > Oh My Cassette is an open-source MCP server (PyPI: `oh-my-cassette`) that lets Claude Code, Codex, OpenCode and Hermes drive the Cassette video editor: import local media
gtm-skillsllms.txtgtm-skills/gtm/public/llms.txt
open-source ecosystem for agentic > Go-To-Market (GTM). Prompts, agent workflows, browser extension, > MCP server, voice templates, and API for B2B sales teams. Open-source core (MIT) > plus premium
ihuzaifashoukatllms.txtihuzaifashoukat/x-use/llms.txt
open-source Python MCP server and CLI for X (Twitter). It uses the operator's authenticated browser session for profile and post research, inbox reads, and reviewed publishing and outreach
kestra-iollms.txtkestra-io/docs/public/llms.txt
versioned URL to retrieve it as plain Markdown. ## Tools & Capability Discovery - [MCP Server Config](https://kestra.io/.well-known/mcp.json): Use this to connect an agent to Kestra's orchestration tools. ## Core model
softsparkllms.txtsoftspark/ai-toolkit/llms.txt
Rules System](kb/reference/language-rules.md) - [Licensing](kb/reference/licensing.md) - [Manifest-Driven Install System](kb/reference/manifest-install.md) - [MCP Editor Compatibility](kb/reference/mcp-editor-compatibility.md) - [MCP Server Templates](kb/reference/mcp-templates.md) - [Medplum Documentation Map](kb/reference/medplum-docs-map.md) - [Merge-Friendly Install Model](kb/reference/merge-friendly-install-model.md) - [Model compatibility
Dynatracellms.txtDynatrace/dynatrace-for-ai/llms.txt
these knowledge skills for the full experience: npx skills add dynatrace-oss/dtctl - Dynatrace MCP server (https://docs.dynatrace.com/docs/shortlink/dynatrace-mcp-server) — Official MCP server for Dynatrace API access. Use this if your
tubecreatellms.txttubecreate/tubecli/docs/llms.txt
experimental and do not depend on it ## Not supported - MCP (Model Context Protocol): no MCP server or client exists in this repository. Any listing that claims MCP support for TubeCLI
tubecreatellms.txttubecreate/tubecli/llms.txt
several ChatGPT subscriptions with automatic failover, sessions in the Flow canvas, and the `tubecli` MCP server ([mcp_relay.py](https://github.com/tubecreate/tubecli/blob/main/tubecli/extensions/codex_gpt/mcp_relay.py)) exposing the Task Board, browser profiles, extensions
swimmwatchllms.txtswimmwatch/cloakbrowser-mcp/docs/llms.txt
variables should use container paths, not host paths. ## GeoIP Proxy Matching Set `PLAYWRIGHT_MCP_PROXY_SERVER` and `CLOAK_PLAYWRIGHT_MCP_GEOIP_PROXY_MATCH=true` to align CloakBrowser timezone, language
alexei-ledllms.txtalexei-led/spotinfo/llms.txt
spotinfo > CLI tool and MCP server that lists and ranks Spot machines on AWS, GCP and Azure from > committed price snapshots. `spotinfo` answers one question: which Spot machine meets
ZIZKA-AI-SLPipes a download into a shellllms.txtZIZKA-AI-SL/ZizkaDB/llms.txt
truth for what an agent actually did, independent of the LLM. AGPL-3.0 (the MCP server is MIT). Runs on Postgres with Docker. Key facts: - Install: `pip install zizkadb
GuyMannDudellms.txtGuyMannDude/mnemo-cortex/llms.txt
github.com/GuyMannDude/mnemo-cortex/tree/master/integrations/ollama-desktop): Terminal launcher with OpenClaw as MCP host. ## Agent Manifests - [INSTALL.md](https://github.com/GuyMannDude/mnemo-cortex/blob/master/INSTALL.md): The install guide, in plain English — server setup plus per-host wiring for Claude Desktop
28naem-delllms.txt28naem-del/mnemosyne/llms.txt
linked, bisect, the poisoning suite and consolidation. `mnemosy demo --classic` runs the 2.0.0 demo. - MCP server for Claude Code (`.mcp.json`), Cursor (`.cursor/mcp.json`) or any MCP client: command `npx`, args
28naem-delllms.txt28naem-del/mnemosyne/site/llms.txt
linked, bisect, the poisoning suite and consolidation. `mnemosy demo --classic` runs the 2.0.0 demo. - MCP server for Claude Code (`.mcp.json`), Cursor (`.cursor/mcp.json`) or any MCP client: command `npx`, args
chattermatellms.txtchattermate/chattermate.chat/llms.txt
reference](https://docs.chattermate.chat/features/cli): the account CLI — signup, login, tokens, agents, workflows, knowledge. - [MCP Server](https://docs.chattermate.chat/features/mcp-server): let an AI agent configure ChatterMate over the Model Context Protocol (`chattermate
nexscope-aillms.txtnexscope-ai/ecommerce-ai-tools/docs/llms.txt
Amazon research API by task, evidence, coverage, access, and cost - https://learn.nexscope.ai/ecommerce-ai-tools/what-is-an-mcp-server/ — MCP concepts, clients, servers, tools, resources, and permissions - https://learn.nexscope.ai/ecommerce-ai-tools/api-capabilities/ — ecommerce API capabilities and evidence boundaries
playcanvasllms.txtplaycanvas/developer-site/llms/llms.txt
scenes, managing assets and publishing apps, with the Editor API, the REST API, the MCP server and the VS Code extension. - [React](/user-manual/react/llms.txt): `@playcanvas/react`, which builds scenes declaratively from React
nirholasllms.txtnirholas/pump-fun-sdk/llms-full.txt
sharing, token incentives, and social fee integrations. Also includes vanity address generators (Rust + TypeScript), MCP server (55 tools), WebSocket relay, live dashboards, 4 Telegram bots, bot fleet orchestrator, AI trading
nirholasllms.txtnirholas/pump-fun-sdk/llms.txt
performance Rust vanity address generator (solana-sdk + rayon) - typescript/ - TypeScript vanity address generator (@solana/web3.js) - mcp-server/ - Model Context Protocol server for AI agents (55 tools, 4 resources, 5 prompts) - telegram
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.
