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.
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
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
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
guardanallms.txtguardana/guardana/site/llms.txt
source AI security verification. Its rule engine scans model artifacts, probes live endpoints and MCP servers, and grades completed agent runs. Use it on a laptop, in CI, or beside
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-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
Googlellms.txtgoogle/three-live/examples/llms-full.txt
magnetic-snap` + `shared-room`) ```html const deck = new THREE.Mesh( new THREE.CylinderGeometry(1.4, 1.4, 0.04, 48), new THREE.MeshStandardMaterial({ color: 0x0f172a, roughness: 0.85 }) ); deck.name = 'walkable-deck'; deck.position.set(0, -0.45, -1.2); deck.userData.xr = { navigable: 'walkable', explode: false, sync: false }; scene.add(deck); const chassis = new THREE.Mesh( new THREE.CylinderGeometry(0.28, 0.32, 0.16, 36), new THREE.MeshStandardMaterial({ color: 0x334155, metalness: 0.75, roughness: 0.25 }) ); chassis.name = 'turbine-chassis'; chassis.position.set(0, 0.75, -1.2); chassis.userData.xr = { dimensions: { unit: 'cm', axes: ['x', 'y', 'z'] }, snapSocket: { tag: 'rotor-bay', radius: 0.18, highlightColor: '#22c55e' }, explode: false }; scene.add(chassis); const shroud = new THREE.Mesh( new THREE.CylinderGeometry(0.24, 0.26, 0.22, 36), new THREE.MeshStandardMaterial({ color: 0x38bdf8, metalness: 0.65, roughness: 0.2 }) ); shroud.name = 'upper-shroud'; shroud.position.set(0, 0.96, -1.2); shroud.userData.xr = { grab: '1-hand', snapTo: { socketTag: 'rotor-bay', radius: 0.18, angleDeg: 15 }, explode: { direction: [0, 1, 0], distance: 0.32, layer: 2, leaderLine: true }, gaze: { dwellMs: 1000, action: 'select' }, anchor: { id: 'upper-shroud', persist: true }, sync: true }; scene.add(shroud); const key = new THREE.DirectionalLight(0xffffff, 2.2); key.position.set(2, 4, 3); scene.add(key); scene.add(new THREE.AmbientLight(0xffffff, 0.6)); ``` -------------------------------------------------------------------------------- ## 5. Closed-Loop AI Agent Verification (`three-live-cli` & MCP Server) AI coding agents can validate, visually inspect, and simulate
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
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
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
Microckllms.txtMicrock/kagi-cli/docs/llms.txt
Embedded, version-matched guidance for agents and automation. - [mcp](https://kagi.micr.dev/commands/mcp): Run kagi-cli as a stdio Model Context Protocol server. - [completion](https://kagi.micr.dev/commands/completion): Complete reference for *kagi
pc-stylellms.txtpc-style/x-md/public/llms.txt
contract: `Accept: application/json` on any read route, described by https://mdfromx.com/openapi.json, or the MCP server at https://mdfromx.com/mcp. How to call it: one plain
thebanrillms.txtthebanri/limoni/llms.txt
style tests against it by role and label, and `limoni-mcp` serves it to MCP clients such as Claude Code and Cursor, so an agent can operate a running
directionally-localllms.txtdirectionally-local/autopilot/docs/llms.txt
semantic code intelligence (hover, go-to-definition, references, diagnostics). - MCP (Model Context Protocol) extensibility for external tool servers. - Explicit, opt-in cross-session memory (SQLite + embeddings). - Session persistence with `/resume
oaslanankallms.txtoaslananka/kicad-mcp-pro/docs/llms.txt
schematic automation, PCB automation, ERC, DRC, DFM, BOM, manufacturing export, live preview, visual evidence, MCP server, Python, PyPI
WatermelonCorpllms.txtWatermelonCorp/watermelon-platform/public/llms.txt
Prefer `search`, `get_inspiration`, `get_component`, `compose_page`, and `list_categories`. - Connect the hosted MCP server with `claude mcp add --transport http watermelon https://mcp.watermelon.sh/mcp` or `codex mcp
paolobietolinillms.txtpaolobietolini/gtm-mcp-server/llms.txt
MCP Server > AI-accessible API for Google Tag Manager. Create tags, audit containers, generate tracking plans, and publish changes — all through natural language. - URL: https://mcp.gtmeditor.com - Protocol: Model Context Protocol
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.
