How real projects summarise themselves for language models.
Lumiwealthllms.txtLumiwealth/lumibot/llms.txt
Python trading and backtesting framework for stocks, options, crypto, futures, forex, and prediction markets. Supports Alpaca, Interactive Brokers, Tradier, Schwab, ThetaData, Yahoo Finance, Polygon, and Polymarket. Includes built-in AI trading…
can4hou6joeng4llms.txtcan4hou6joeng4/boss-agent-cli/demo/llms.txt
A local-assist BOSS Zhipin CLI built for AI agents. Search, welfare filtering, and shortlist organizing emitted as a structured JSON envelope. Low-risk by default: local-assist, read-only-first, user-triggered.
NVIDIAllms.txtNVIDIA/aistore/docs/llms.txt
AIStore (AIS) is a lightweight, open-source distributed object storage system by NVIDIA designed for AI/ML workloads. It provides multi-cloud unified access (AWS S3, GCS, Azure, OCI), linear scalability, high-performance I/O with no routing overhead, and AI-optimized features including sharding, ETL, batch operations, and PyTorch/TensorFlow integration. - Distributed Sort (dSort): Reshard and shuffle massive datasets - Blob Downloader: Chunked parallel downloads of large remote objects - Get-Batch: Bulk object retrieval for training data pipelines -
Microsoftllms.txtmicrosoft/WhatTheHack/068-AzureOpenAIApps/Student/Resources/data/mcp-info/llms-full.txt
A list of applications that support MCP integrations This page provides an overview of applications that support the Model Context Protocol (MCP). Each client may support different MCP features, allowing for varying levels of integration with MCP servers.
CoderGamesterllms.txtCoderGamester/mcp-unity/llms.txt
MCP Unity is an open-source implementation of the Model Context Protocol (MCP) for the Unity Editor. It connects a C# Unity Editor package with a Node.js/TypeScript server over WebSockets and exposes high-level "tools" and "resources" so language-model agents and other automated clients can safely inspect, test, and modify Unity projects in real-time. This repository consists of two coordinated halves that communicate using JSON-encoded MCP messages: - Editor/ – Unity package that starts an internal WebSocket server and registers C# MCP…
NVIDIAllms.txtNVIDIA/dcgm-exporter/llms.txt
This file is for LLMs and agents generating or modifying DCGM Exporter metrics, configuration, deployment examples, and validation plans. Current repository code and checked-in artifacts are the mechanical source of truth. Do not invent flags, environment variables, metric labels, DCGM field names, exporter-owned counter names, Helm values, or package behavior. If required facts are not present in this repository, mark them unknown and ask for source material. Use this order: 1. pkg/cmd/app.go defines CLI flags, environment variables, defaults, startup behavior,…
Alisa0808llms.txtAlisa0808/vox-director/llms.txt
An open-source agent skill that turns ONE topic into a finished Vox-style paper-collage explainer / ad video — script, collage keyframes, motion, voice-over, music and captions — automated end to end on the Atlas Cloud API + local ffmpeg. Works with any coding agent (Claude Code, Codex, and any SKILL.md agent).
OpenOSINTllms.txtOpenOSINT/OpenOSINT/llms.txt
No summary in the file. Open it to read it.
Priivacy-aillms.txtPriivacy-ai/spec-kitty/docs/llms.txt
Spec Kitty is the current documentation set for the Spec Kitty CLI, Charter governance model, AI harness integration, mission runtime, and project upgrade workflows. The docs are organized into a single 13-section Common Docs structure under one entry point. The docs are a single 13-section Common Docs structure: When the question is about X, read Y first (each section has its own index.md landing page):
patrickchughllms.txtpatrickchugh/terravision/docs/llms-full.txt
TerraVision draws professional cloud architecture diagrams using the official AWS, Azure and GCP icon sets. Input is either a plain JSON graph (each key is <terraformresourcetype>.<name>, each value the list…
patrickchughllms.txtpatrickchugh/terravision/docs/llms.txt
TerraVision draws professional cloud architecture diagrams using the official AWS, Azure and GCP icon sets. Input is either a plain JSON graph (each key is <terraformresourcetype>.<name>, each value the list…
koreainvestmentllms.txtkoreainvestment/open-trading-api/llms.txt
Python examples and utilities for the KIS Open API, supporting automated trading, market data retrieval, account management, and strategy development.
Vercelllms.txtvercel-labs/dev3000/www/llms.txt
AI-powered development tools with comprehensive browser monitoring and skill-based agent guidance dev3000 is a TypeScript package that gives AI assistants deep visibility into local development workflows. It captures unified logs from servers, browsers, and user interactions, making debugging and development assistance dramatically more effective. All logs use unified timestamps with source prefixes: dev3000 is specifically designed to enhance AI-assisted development:
fujibeellms.txtfujibee/agmsg/llms.txt
Cross-agent messaging for CLI AI agents. Claude Code, Codex, Gemini CLI, GitHub Copilot CLI, Antigravity, and OpenCode message each other directly through a shared local SQLite database — no daemon, no network, no MCP. Just bash + sqlite3. Everyday commands (same across agents; shown here as the Claude Code /agmsg form): Alternate installs: npx agmsg (or npm i -g agmsg && agmsg install), or the Claude Code plugin marketplace (/plugin marketplace add fujibee/agmsg). All paths land at ~/.agents/skills/agmsg/. See README.md…
fynnflueggellms.txtfynnfluegge/agtx/llms-full.txt
Terminal kanban board that orchestrates multiple AI coding agents in parallel. agtx manages coding agent sessions through a spec-driven workflow with phases: backlog, planning, implementation (running), review, and done. Each task gets its own git worktree and tmux window so agents run simultaneously without interfering with each other. agtx runs as a TUI (terminal user interface) built in Rust. It manages: Moving a task between phases starts the configured agent for that phase. Different agents can handle different phases (e.g.…
fynnflueggellms.txtfynnfluegge/agtx/llms.txt
Terminal kanban board that orchestrates multiple AI coding agents in parallel. agtx manages coding agent sessions through a spec-driven workflow: backlog, planning, implementation, review, done. Each task gets its own git worktree and tmux window, so agents run simultaneously without conflicts.
umputunllms.txtumputun/ralphex/llms.txt
Autonomous plan execution with Claude Code. Executes implementation plans task by task in fresh Claude sessions, then runs multi-phase code reviews. Write a plan, start ralphex, walk away. GitHub: https://github.com/umputun/ralphex
najmuzzaman-mohammadllms.txtnajmuzzaman-mohammad/gawkbot/website/llms.txt
gawkbot is the open source Grok Bot. gawkbots automate your menial work via AI models and build you microapps to manage the outcome, so that you have a false sense…
mnemox-aillms.txtmnemox-ai/tradememory-protocol/llms.txt
Platform-agnostic AI trading memory system with Outcome-Weighted Memory (OWM) architecture via MCP. Accepts standardized trade data from any source (MT5, Binance, Alpaca) and provides structured memory with LLM-powered reflection. TradeMemory Protocol is an open-source memory layer for AI-assisted trading systems. It does NOT connect to trading platforms directly — it accepts standardized trade data and organizes it into three layers: Key capabilities: - 4 MCP tools: storetrade, recalltrades, getperformance, runreflection - LLM-powered reflection engine (Claude API) for trade analysis -…
razzantllms.txtrazzant/ouroboros/docs/llms.txt
Ouroboros is an open-source AI agent with a continuing identity, durable memory, agent swarms, autonomous evolution, and an implementation it can rewrite. Canonical site: https://ouroboros-agent.ai/ Source: https://github.com/razzant/ouroboros License: MIT Ouroboros publishes self-reported benchmark results with status labels and links to available runs, traces, methodology, and submissions. The GAIA result states that its scrubbed trace capsule is pending. Upstream leaderboard acceptance is reported separately when it happens.
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.
