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.
arthjeanllms.txtarthjean/paneflow/llms.txt
install paths, core workflows, safety model. - [Architecture](ARCHITECTURE.md) - runtime architecture, threading, terminal pipeline, IPC, security posture. - [Agent Instructions](AGENTS.md) - repository rules for coding agents working in this codebase. - [MCP Bridge
dykyi-romanllms.txtdykyi-roman/awesome-claude-code/llms.txt
patterns - CI/CD: pipeline, tools, deployment - Docker: core, multistage, base-images, php-extensions, compose, networking, security, buildkit, production, troubleshooting, orchestration, scanning - Frameworks: Symfony, Laravel, Yii, CodeIgniter, No-Framework (pure PHP) - Task
rasimmellms.txtrasimme/FlowBoard/llms.txt
backoff and session-safe routing - [Telegram Mini App](docs/concepts/telegram-mini-app.md) — ordered multi-bot HMAC auth; secure sessions; tunnel access ## Decisions (ADRs) - [ADR-0001](docs/adr/0001-live-inject-bootstrap.md) — Project context delivered via live-inject
akutishevskyllms.txtakutishevsky/nutrition-mcp/public/llms.txt
rate limits, barcode lookups, export links, account deletion, and where to report bugs and security issues. - [Apple Health sync](https://nutrition-mcp.com/apple-health): Setup guide for the optional Nutrition MCP Health
jangtrinhllms.txtjangtrinh/design-os-studio/docs/llms-full.txt
first launch asks for a one-time Open Anyway in System Settings > Privacy & Security. ### When not to use - Real-time multi-user cloud whiteboarding requiring hosted WebRTC multiplayer cursors without
major7appsllms.txtmajor7apps/pensyve/llms.txt
service are unavailable. The open-source project is in maintenance mode, with security fixes and dependency updates but no new features. The Rust engine stores memories in SQLite by default
ParthibanRajasekaranllms.txtParthibanRajasekaran/text-from-image/public/llms.txt
self-hosted. English language data ships with the package. - Network: the site's Content Security Policy limits connections to its own origin. The SDK, command line and MCP server make
escapeboyllms.txtescapeboy/claude-code-kit/llms.txt
keeps a `## Tasks` checklist it reads - [Subagents](https://github.com/escapeboy/claude-code-kit/tree/master/10-subagents/examples): 8 agent definitions → `~/.claude/agents/` - [Security hooks](https://github.com/escapeboy/claude-code-kit/tree/master/13-security-hardening/hooks): PreToolUse guards with tests - [Productivity hooks](https://github.com/escapeboy/claude-code-kit/tree/master/01-global-optimization/hooks): shell-habits
hyperb1issPipes a download into a shellllms.txthyperb1iss/lucidity-mcp/docs/llms-full.txt
Tool integration for executing commands and scripts * Local server connections for enhanced privacy and security > ⓘ Note: The Claude.ai web application does not currently support MCP. MCP features are only
ridgesaiReads credentialsllms.txtridgesai/ridges/llms.txt
Ridgeline job dispatch](https://docs.ridges.ai/ridgeline/dispatch-a-job.md) - [Ridgeline prompts](https://docs.ridges.ai/ridgeline/writing-good-prompts.md) - [Ridgeline privacy and security](https://docs.ridges.ai/ridgeline/privacy-and-security.md) - [Ridgeline FAQ](https://docs.ridges.ai/ridgeline/faq.md) - [Ridges website](https://www.ridges.ai
HorizunGroupllms.txtHorizunGroup/horizun-revit-mcp/llms.txt
/HorizunGroup/horizun-revit-mcp/blob/main/docs/INSTALL.md - Tool catalogue: https://github.com/HorizunGroup/horizun-revit-mcp/blob/main/docs/TOOLS.md - Contributing: https://github.com/HorizunGroup/horizun-revit-mcp/blob/main/CONTRIBUTING.md - Benchmark: https://github.com/HorizunGroup/horizun-revit-mcp/blob/main/docs/BENCHMARK.md - Security model: https://github.com/HorizunGroup/horizun-revit-mcp/blob/main/docs/security-model.md - Family authoring: https://github.com/HorizunGroup/horizun-revit-mcp/blob/main/docs/FAMILY-AUTHORING.md - DWG to BIM: https://github.com/HorizunGroup/horizun-revit-mcp/blob/main/docs/DWG-TO-BIM.md
jorgerosalllms.txtjorgerosal/wordpress-skills/docs/llms.txt
WordPress Skills > WordPress skills for Claude Code and Codex. > Focus: plugin review, WooCommerce, security, performance, REST API, migrations, testing, WP-CLI ops, Playground, and PHPStan. ## Primary pages - Homepage: https://jorgerosal.github.io
trustablllms.txttrustabl/agent-reliability-analyzer/llms.txt
open-source tool for AI agent reliability: it finds the > reliability, safety, and security defects in an agent codebase and > automatically fixes them. It discovers a repo's agent/tool inventory
vitalopsllms.txtvitalops/opendesk/llms.txt
Remote via MCP](https://vitalops.ai/opendesk/docs/remote/mcp.html): opendesk_peers, opendesk_use, the `peer` argument - [Remote security](https://vitalops.ai/opendesk/docs/remote/security.html): X25519 pairing, ChaCha20-Poly1305 frames - [Remote control (JS)](https://vitalops.ai/opendesk/docs/remote-js/index.html):
ClickHousellms.txtClickHouse/loom/llms.txt
full replica behind one URL, and an upgrade replaces them one at a time. - [Security](docs/architecture/security.md): Loom separates tenants by columns: every row carries the identity tuple, and every read
ThreeMoonsLabllms.txtThreeMoonsLab/agents-shipgate/llms.txt
eval framework. - Not a runtime guardrail. - Not an LLM gateway. - Not a security audit. - Not a compliance certification. - Not a SOC, ISO, or HIPAA toolkit. - Does not invoke models. - Does
MikkoParkkolaReads credentialsllms.txtMikkoParkkola/mcp-gateway/llms.txt
breakers, retry, rate limiting, health checks - Web dashboard at /ui, operator dashboard at /dashboard - Security: bearer tokens, API keys, per-client tool scopes, credential redaction, prompt injection detection - Transports: stdio
AsiaOstrichllms.txtAsiaOstrich/universal-dev-standards/llms.txt
Message Guide](https://github.com/AsiaOstrich/universal-dev-standards/blob/main/core/commit-message-guide.md): `commit-message-guide`, level 1 - [Container Image Build and Security Standards](https://github.com/AsiaOstrich/universal-dev-standards/blob/main/core/container-image-standards.md): `container-image-standards`, level 2 - [容器安全標準](https://github.com/AsiaOstrich/universal-dev-standards/blob/main/core/container-security.md): `container-security
backenlyllms.txtbackenly/backenly/public/llms.txt
list of problems on its own (a missing index, a table without row-level security, a missing realtime trigger), verifying each fix. Anything else becomes a finding with evidence
nirholasReads credentialsllms.txtnirholas/agenti/llms-full.txt
Keypair } from '@solana/web3.js' import bs58 from 'bs58' // Generate a fresh wallet: store these keys securely const wallet = generateWallet() console.log('EVM: ', wallet.evm.address) console.log('Solana: ', wallet.solana.address) console.log('Key: ', bs58.encode(wallet.solana.privateKey)) // Phantom-compatible
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.
