How real projects summarise themselves for language models.
manor-osllms.txtmanor-os/manor-ai/llms.txt
solopreneurs, lean teams, and technical operators. It connects AI agents with goals, tasks, plans, documents, knowledge, tools, workflows, integrations, execution history, and human approvals. The canonical public product name
tubecreatellms.txttubecreate/tubecli/docs/llms.txt
pending_approval` queue that a human must accept with `approve ` before it runs. ## Documentation - [README](https://raw.githubusercontent.com/tubecreate/tubecli/main/README.md): what TubeCLI is, install steps, capability list, comparison table and FAQ - [Extension
selfishprimatellms.txtselfishprimate/gerillass/llms.txt
readable manifest whose examples and refusals are executed by the test suite, so the documentation cannot drift away from the code. Gerillass is a pure Sass library. There
smnandrellms.txtsmnandre/symfony-ux-skills/llms.txt
agentskills.io open standard. Covers Symfony UX 2.22--2.28+, Symfony 7.2/7.4/8.0, PHP 8.4+. ## Documentation - [Symfony UX Orchestrator](skills/symfony-ux/SKILL.md): Decision tree for choosing between Stimulus, Turbo, TwigComponent, LiveComponent, Icons
alfadur7llms.txtalfadur7/llm-wiki-newsroom/docs/llms.txt
knowledge production: a multi-agent "newsroom" on Claude Code that turns a folder of documents into a cross-linked, human-readable markdown wiki. The agent that writes a page
paolobietolinillms.txtpaolobietolini/gtm-mcp-server/llms.txt
workflow (workspace → diff → version → approved publish) | | `generate_tracking_plan` | accountId, containerId, workspaceId | Generate markdown documentation of all events, triggers, variables | | `suggest_ga4_setup` | goals (text description) | Recommend GA4 tag structure
oliver-zehentleitnerllms.txtoliver-zehentleitner/keep-the-why/llms.txt
black box only one person ever understood. Because "ask Bob" is not documentation. Keep a Changelog records what changed; Keep the Why preserves why it changed. Complements README, AGENTS.md, docs
pc-stylellms.txtpc-style/x-md/public/llms.txt
true`, and structured JSON with `?format=json` or `Accept: application/json`. Canonical site: https://x.pcstyle.dev/ Documentation: https://x.pcstyle.dev/docs Source: https://github.com/pc-style/x-md ## When to use x.md Reach for x.md when
antropos17llms.txtantropos17/Aegis/llms-full.txt
contact GitHub. AEGIS has manual process controls but no automatic OS-level enforcement. This document describes current source. Installed releases can lag behind it; consult the release tag and README
antropos17llms.txtantropos17/Aegis/llms.txt
policy checks. Monitoring combines polling with event-based file watchers; coverage and attribution have documented limits. Current source also provides opt-in exact-action execution policies and explicitly configured
Continuellms.txtcontinuedev/amplified.dev/llms.txt
file, the checks in this repo, the way contributions work — these aren't just documentation. They're a feedback loop: human taste encoded as standards, enforced with your help, with
ayush-thatllms.txtayush-that/sub-agents.directory/public/llms.txt
script that installs the prompt into `~/.claude/agents`. - [OpenAPI specification](https://sub-agents.directory/openapi.json): machine-readable documentation for the public API. - [Developer resources](https://sub-agents.directory/developers): human-readable API and discovery documentation
heypandaxllms.txtheypandax/cc-pocket/site/llms.txt
options - Anthropic offers Claude Code Remote Control. Its official guide, checked 2026-07-13, documents `/remote-control` and `claude remote-control`, Claude Code 2.1.51+, and Pro / Max / Team / Enterprise eligibility. - OpenAI
hidai25llms.txthidai25/eval-view/llms-full.txt
EvalView — Complete Documentation for AI Systems > Regression testing for AI agents. Snapshot behavior, detect regressions, block broken agents before production. ## Identity - Name: EvalView - Tagline: "Proof that your agent still works
hidai25llms.txthidai25/eval-view/llms.txt
Team (hidai@evalview.com) ## Links - Homepage: https://evalview.com - GitHub: https://github.com/hidai25/eval-view - PyPI: https://pypi.org/project/evalview/ - Documentation: https://github.com/hidai25/eval-view#readme - Issues: https://github.com/hidai25/eval-view/issues - Discussions: https://github.com/hidai25/eval-view/discussions - Starter Template: https://github.com
deepnoodle-aillms.txtdeepnoodle-ai/dive/llms.txt
calling system aligned with Claude Code patterns, and an agent loop with hooks. Images, documents, and structured output work across all providers. The library does not install a persona
poemswellms.txtpoemswe/co-researcher/llms-full.txt
development - Thematic analysis: theme identification, saturation assessment, negative case analysis - Reflexivity: prompts researcher positionality documentation - Output: codebook, theme map, saturation assessment, reflexivity memo ### Peer Review (`/review`) Structures feedback
Bande-a-Bonnotllms.txtBande-a-Bonnot/Boucle-framework/docs/llms.txt
boundary hooks, start a fresh Claude Code session from the same project root and document residual warnings instead of reinstalling repeatedly to chase an A. - Hooks cover Claude Code tool
chattermatellms.txtchattermate/chattermate.chat/llms.txt
app.chattermate.chat - Hosted API base: https://api.chattermate.chat (routes under `/api/v1`) - Widget script: https://app.chattermate.chat/webclient/chattermate.min.js - Documentation: https://docs.chattermate.chat - GitHub: https://github.com/chattermate/chattermate.chat ## Self-hosting (optional) - [Self-host with Docker](https://docs.chattermate.chat
SkeneTechnologiesllms.txtSkeneTechnologies/skene/docs/llms.txt
feature-registry.json — Persistent feature registry tracking features across analysis runs product-docs.md — User-facing feature documentation (with --product-docs flag) ## Key Concepts Growth Manifest (v1.0): project_name, description, tech_stack (framework, language
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.
