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.
veelengallms.txtveelenga/claude-mermaid/docs/llms.txt
Claude Mermaid > claude-mermaid is an MCP (Model Context Protocol) server that renders Mermaid diagrams in the browser with live reload as Claude edits the code. It exposes two tools
jenticllms.txtjentic/jentic-one/llms.txt
skill it generates. Second: over MCP, either the CLI's local stdio server (`jentic mcp`) or the deployment's own Streamable HTTP `/mcp` endpoint, which is config-gated
southleftllms.txtsouthleft/design-systems-mcp/public/llms.txt
guidance-layer documentation, not prop tables - Agent-interface protocols: A2UI v1.0, MCP Apps (SEP-1865), AG-UI, server-driven UI lineage - Practice: component contracts, source-of-truth debate, Context-Based
alexei-ledllms.txtalexei-led/k8s-mcp-server/llms.txt
MCP Server > MCP server for Kubernetes CLI tools — kubectl, Helm, istioctl, and ArgoCD — with security policies and Unix pipe support. K8s MCP Server implements the Model Context Protocol (MCP
dylanroscoverllms.txtdylanroscover/Embody/web/llms-full.txt
Envoy + TDXN - full text for AI agents > Open-source TouchDesigner toolkit. Envoy is an MCP server (54 tools) that lets AI > assistants build, wire, parameterize, and debug a LIVE TouchDesigner
dylanroscoverllms.txtdylanroscover/Embody/web/llms.txt
open-source TouchDesigner toolkit - "create at the speed of thought." Envoy is an embedded MCP server that connects AI coding tools to a live TouchDesigner session; Embody externalizes the network
ruixenuillms.txtruixenui/ruixen.com/public/llms-full.txt
ruixen.com/docs/installation - **Tailwind v4 Guide:** https://ruixen.com/docs/tailwind-v4 - **UI Library Guide:** https://ruixen.com/docs/ui-library - **MCP Server:** https://ruixen.com/docs/mcp ### Tools & Generators - **Glass Morphism Generator:** https://ruixen.com/generator/glass-morphism - **Shadow Generator
Kayforkindllms.txtKayforkind/reimagine-it/docs/llms.txt
reimagine-it audit out.html` | 19 deterministic craft checks (exit 0/1/2) | | `npx reimagine-it mcp` | MCP server, 8 tools, stdio | ## Rules an agent must follow 1. Run Auto first (`--auto`); read
mercurialsoloReads credentialsllms.txtmercurialsolo/claudectl/docs/llms.txt
runtime crates in the sync core, no async runtime except the two MCP stdio servers (claudectl bus stdio, claudectl query stdio), which each build their own current-thread Tokio runtime
runesleollms.txtrunesleo/polymarket-toolkit/llms.txt
three agent skills, a TypeScript helper library, and a 12-tool read-only MCP server for inspecting public Polymarket data without exposing order placement to AI chat tools. Last verified
tsubotaxllms.txttsubotax/melta-ui/llms-full.txt
ツール用の集約データ | | MCP `melta://design-constitution` レスポンス | `DESIGN.md` | MCP だけで接続する AI の最初の入口（runtime 直読、内容の複製なし） | | MCP `melta://rules` レスポンス | `design/contracts/rules.json` | AI エージェントからのルール参照 | | `docs/` の component count・nav | contracts + tokens | 公開サイト表示 | | `llms.txt
nikolai-vysotskyiReads credentialsllms.txtnikolai-vysotskyi/trace-mcp/docs/llms-full.txt
file instead of following links. See /llms.txt for the linked index. --- # Code graph MCP server for AI coding agents Source: https://trace-mcp.com/code-graph-mcp.html A **code graph MCP server** indexes
nikolai-vysotskyillms.txtnikolai-vysotskyi/trace-mcp/docs/llms.txt
from the served file. layout: null --- # trace-mcp > trace-mcp is a framework-aware MCP server that serves precomputed code intelligence — a dependency graph, full-text search, impact analysis
wesmllms.txtwesm/middleman/docs/llms.txt
fleet, how ownership works, and how to set it up - [MCP companion](https://forge.kenn.io/docs/kenn-forge-mcp.md): Model Context Protocol server for agent access to the console - [GitHub CLI shim](https://forge.kenn.io
mahdin75llms.txtmahdin75/gis-mcp/docs/llms-full.txt
MCP Server > GIS MCP is an open-source Model Context Protocol server for GIS/geospatial analysis and AI agents. GIS MCP (GIS MCP Server) lets AI agents run real GIS workflows
mahdin75llms.txtmahdin75/gis-mcp/docs/llms.txt
MCP Server > GIS MCP is an open-source Model Context Protocol server for GIS/geospatial analysis and AI agents. Install with `pip install gis-mcp`. Default transport is STDIO (`gis-mcp
missingus3rllms.txtmissingus3r/friday-showcase/llms.txt
Memory** — Flask + SQLite + embedding-based hybrid RAG (FTS5 + vector cosine, RRF) - **Knowledge** — Notion (via MCP plugin) - **Code graph** — graphify (knowledge graph of codebases and docs, Claude Code skill) - **Voice** — ElevenLabs
AGIHuntPipes a download into a shellllms.txtAGIHunt/blurt/site/llms.txt
worktree per item. Review the changes, then merge. - Agents report through Blurt's MCP server: In progress, then To verify. MCP tools: search_items, get_item, get_transcript, update_item
tmseidelllms.txttmseidel/ai-git-bot/llms-full.txt
back to the Git platform. It centralizes configuration, credentials, prompts, bot personas, sessions, optional MCP server tool access, per-bot tool whitelists, workflow audit trails, and outgoing webhook subscriptions
tmseidelllms.txttmseidel/ai-git-bot/llms.txt
Anthropic Claude, OpenAI, Google AI / Gemini, Ollama, and llama.cpp. - Optional Model Context Protocol (MCP) server integration with persisted tool whitelists. - Optional per-bot user whitelist to restrict who may trigger
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.
