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.
NirDiamantllms.txtNirDiamant/agents-towards-production/llms.txt
github.com/NirDiamant/agents-towards-production/tree/main/tutorials/LangGraph-agent): Building a stateful agent as a graph with LangGraph. - [Agent with MCP](https://github.com/NirDiamant/agents-towards-production/tree/main/tutorials/agent-with-mcp): Connecting an agent to tools over the Model Context Protocol. - [A2A](https://github.com
Evil0ctalllms.txtEvil0ctal/Douyin_TikTok_Download_API/llms.txt
Bilibili (B 站). One > `docker compose up` gives you a REST API, an MCP server and a web console, > backed by an identity pool (cookies + proxies + fingerprints) that mints, > tests
datawhalechinaReads credentialsllms.txtdatawhalechina/easy-vibe/llms.txt
Model Context Protocol、工具调用、Claude、Claude Code、外部工具、工具定义、Tool Definition、Function Calling、工具生态、MCP Server、MCP Client、上下文协议、AI 工具链、核心技能、core-skills **内容概要**: MCP 协议的完整使用指南 --- #### 3.0 Agent 团队
No other project uses it yet
xerj-orgReads credentialsllms.txtxerj-org/xerj/landing/llms-full.txt
returns cited answers. Last updated: 2026-10-23 (canonical description, ES-YAML and MCP tool counts synced; hub section run on v1.0.0-rc.97). When this file and the binary disagree
xerj-orgPipes a download into a shellllms.txtxerj-org/xerj/landing/llms.txt
command) `xerj init` wires XERJ into the coding agents in the project: registers the MCP server in `.mcp.json` and writes a 10-line skill for Claude Code/Cursor, with .bak backups
corsairdevllms.txtcorsairdev/corsair/docs/llms.txt
docs.corsair.dev/mcp-adapters/claude-sdk.md): Use Corsair with the Claude Agent SDK via an in-process MCP server. - [Vercel AI SDK](https://docs.corsair.dev/mcp-adapters/vercel-ai.md): Connect Corsair to the Vercel AI SDK over HTTP
tonhowtfReads credentialsllms.txttonhowtf/omniget/llms-full.txt
github.com/tonhowtf/omniget#the-browser-extension-step-by-step) - [The Tools section: 156 tools in 24 categories](https://github.com/tonhowtf/omniget#the-tools-section-156-tools-in-24-categories) - [MCP server for Claude Code, Cursor and VS Code, and a Claude Code plugin](https://github.com/tonhowtf/omniget#omniget-for-ai-agents-mcp-server-and-claude-code-plugin)
No other project uses it yet
tonhowtfllms.txttonhowtf/omniget/llms.txt
permissions, undo, durable jobs, loops that repeat until a test command passes, an embedded MCP server with 49 tools, and an isometric house called the World where the agents
No other project uses it yet
yichuan-wllms.txtyichuan-w/LEANN/llms.txt
/StarTrail-org/LEANN contact: https://github.com/StarTrail-org/LEANN/issues # Installation install: uv tool install leann-core --with leann # MCP Server Entry Point mcp.server: leann_mcp mcp.protocol_version: 2024-11-05 # Tools mcp.tools: leann_list
No other project uses it yet
NangoHQReads credentialsllms.txtNangoHQ/nango/docs/llms-full.txt
backend jobs, or agents then consume those functions through Nango's API, SDKs, or MCP server. Nango supports [1,000+ APIs](/integrations/overview) and handles auth, credentials, execution, retries, rate limits
NangoHQllms.txtNangoHQ/nango/docs/llms.txt
tokens are revoked. - [Auth: MCP Auth](https://nango.dev/docs/guides/auth/mcp-auth.md): Let your users connect to MCP servers through Nango - [Agent sessions](https://nango.dev/docs/guides/agent-sessions.md): Optimized interface for AI agents
DuarteSantos8Reads credentialsllms.txtDuarteSantos8/openGym/website/llms.txt
/docs.html): every feature, self-hosting, every .env setting, AI Coach, imports (FitNotes/Strong/Hevy/Apple Health), backups, MCP server, troubleshooting - [HTTP API](https://opengym.ch/api.html): OpenAPI spec, also at [openapi.yaml](https://opengym.ch/openapi.yaml)
Steady16 mentions in 2 weeks
No other project uses it yet
tw93llms.txttw93/Kami/site/llms.txt
Kami API, no account, and no API key: the integration surface is a local MCP server, JSON content schemas, and CLI checks. ## When to use Kami Reach for Kami when
Steady6 mentions in 2 weeks
No other project uses it yet
chaitanyagirillms.txtchaitanyagiri/munder-difflin/docs/llms-full.txt
Giri. ## What it does New in 0.5.6: Capabilities (Pro), a marketplace of 2,347 MCP servers, skills, plugins and tools from the public list HarnessMD/awesome-agent-capabilities, 622 of them reviewed
1 project uses a version of this
chaitanyagirillms.txtchaitanyagiri/munder-difflin/docs/llms.txt
Studio or vLLM. New in 0.5.6: Capabilities (Pro), a marketplace of 2,347 MCP servers, skills, plugins and tools from the public list HarnessMD/awesome-agent-capabilities, 622 of them reviewed
lastmile-aiReads credentialsllms.txtlastmile-ai/mcp-agent/LLMS.txt
/news/model-context-protocol) - a standardized interface to let any software be accessible to AI assistants via MCP servers. 2. [Building Effective Agents](https://www.anthropic.com/research/building-effective-agents) - a seminal writeup on simple, composable patterns
No other project uses it yet
joemccannReads credentialsllms.txtjoemccann/dillinger/public/llms.txt
Markdown → styled HTML document - POST /convert — HTML → clean markdown OpenAPI spec: https://dillinger.io/api/v1/openapi ## MCP Server Install: npm install @dillinger/mcp Run: DILLINGER_API_KEY= npx @dillinger/mcp Tools: render_markdown, export
No other project uses it yet
zumerlabllms.txtzumerlab/snapdom/docs/llms-full.txt
# SnapDOM: v3 reference Last updated: 2026-10-05. SnapDOM is a browser capture engine
Steady24 mentions in 2 weeks
No other project uses it yet
sparcklesllms.txtsparckles/Robyn/llms.txt
reference/authentication.mdx` - Auth patterns - `api_reference/openapi.mdx` - OpenAPI docs - `api_reference/agents.mdx` - AI agent integration - `api_reference/mcps.mdx` - MCP server guide - `example_app/` - Full example application tutorial
Steady5 mentions in 2 weeks
No other project uses it yet
jokob-skllms.txtjokob-sk/NetAlertX/front/llms.txt
NetAlertX MCP Setup NetAlertX is a network monitoring system. Connect to its **MCP (Model Context Protocol) server** for live access to devices, scans, and events. ## 1. Gather Connection Details
1 project uses a version of this
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.
