How real projects summarise themselves for language models.
Dynatracellms.txtDynatrace/dynatrace-for-ai/llms.txt
/Dynatrace/dynatrace-for-ai > Format: Agent Skills (https://agentskills.io) ## What is Dynatrace Dynatrace is an observability and security platform that provides full-stack monitoring including application performance, infrastructure, logs, digital experience
antropos17llms.txtantropos17/Aegis/llms-full.txt
sequence loader currently does not reject cross-file duplicates. ## Documentation - [README](https://github.com/antropos17/Aegis/blob/master/README.md) - [Security Policy](https://github.com/antropos17/Aegis/blob/master/SECURITY.md) - [Contributing Guide](https://github.com/antropos17/Aegis/blob/master/CONTRIBUTING.md) - [Code of Conduct](https://github.com/antropos17/Aegis/blob/master/CODE_OF_CONDUCT.md)
antropos17llms.txtantropos17/Aegis/llms.txt
github.com/antropos17/Aegis/blob/master/README.md) - [Documentation index](https://github.com/antropos17/Aegis/blob/master/docs/README.md) - [Guided desktop workflows](https://github.com/antropos17/Aegis/blob/master/docs/OBSERVATORY-GUIDED-WORKFLOWS.md) - [Security Policy](https://github.com/antropos17/Aegis/blob/master/SECURITY.md) - [Contributing Guide](https://github.com/antropos17/Aegis/blob/master/CONTRIBUTING.md) - [Code of Conduct](https://github.com/antropos17/Aegis/blob/master/CODE_OF_CONDUCT.md)
KryptosAIllms.txtKryptosAI/mcp-observatory/llms.txt
Observatory MCP Observatory is a free, local-first CI and security gate for Model Context Protocol (MCP) servers before AI agents depend on them. ## Use This When - You maintain
heypandaxllms.txtheypandax/cc-pocket/site/llms.txt
client connects to the daemon directly; the relay is the from-anywhere fallback. ## Security model and honest limits - **End-to-end encryption** between client and daemon: P-256 ECDH + HKDF
Houseofmvpsllms.txtHouseofmvps/claude-rank/llms.txt
scanners for search optimization, AI citability, keyword analysis, content briefs, performance, mobile, and security auditing. All commands accept URLs or local directories. ## Scanners - **SEO Scanner** (54 rules): Meta tags, title/description
sandbaseaillms.txtsandbaseai/deepseek-harness-handbook/site/llms.txt
/deepseek-harness-handbook/deepseek-harness-plugin-audit.html): Bind runtime verdicts to exact package and runner evidence, keep compatibility distinct from security review, authorize Host mutations, diff the resolved composition, and prove rollback and cleanup. - [Install DeepSeek
pleaseaillms.txtpleaseai/shunt/wiki/llms-full.txt
# shunt full documentation ## Overview Configuration exists to keep shunt generic: new upstreams are provider
sinewaveaillms.txtsinewaveai/agent-security-scanner-mcp/llms.txt
agent-security-scanner-mcp > MCP server providing real-time security scanning for AI coding agents. Detects vulnerabilities, hallucinated packages, and prompt injection across 12 languages. ## Tools - scan_security: Scan
Houseofmvpsllms.txtHouseofmvps/ultraship/llms.txt
debugging, AI-powered code review, and a pre-deploy quality gate that scans SEO, security, performance, code quality, and browser testing in one command. ## How to install Ultraship? Install
OraclesTechllms.txtOraclesTech/guardian-sdk/llms.txt
default) or JSON — for a SIEM or a vendor security review. Team and Enterprise plans only. Defaults to the last 30 days; max 366 days, 100,000 rows. --- ## Agent Self
BingoWonllms.txtBingoWon/apple-rag-mcp/public/llms.txt
hybrid technology understands context and provides accurate, relevant answers from Apple's documentation. **Always Secure**: MCP authentication ensures trusted access for your AI agents with enterprise-grade security. **Code Examples
OthmaneBlialllms.txtOthmaneBlial/awesome-openclaw-examples/site/llms.txt
Examples > 300 research-informed, inspectable OpenClaw workflow starter packs with prompts, sample outputs, KPIs, security notes, failure modes, and rollback guidance. ## Canonical pages - https://othmaneblial.github.io/awesome-openclaw-examples/ — project overview and starting
hermes-labs-aillms.txthermes-labs-ai/lintlang/llms-full.txt
README, CHANGELOG, LICENSE (and other licence, NOTICE and third-party notice files), CONTRIBUTING, and SECURITY are skipped. Python test code (`tests/`, `test_*.py`, `*_test.py`, `conftest.py`) is returned as SKIPPED during
luongnv89llms.txtluongnv89/context-stats/docs/llms.txt
/luongnv89/context-stats/blob/main/CHANGELOG.md): Version history ## Optional - [Contributing](https://github.com/luongnv89/context-stats/blob/main/CONTRIBUTING.md): How to contribute to the project - [Security Policy](https://github.com/luongnv89/context-stats/blob/main/SECURITY.md): Security reporting and policies - [License](https://github.com/luongnv89/context-stats/blob/main/LICENSE): MIT License
Kilbexllms.txtKilbex/Vigla/llms-full.txt
land in under two hours. Questions and bug-report routing: [SUPPORT.md](https://github.com/Kilbex/Vigla/blob/main/SUPPORT.md). Security reports: see [SECURITY.md](https://github.com/Kilbex/Vigla/blob/main/SECURITY.md). Reviewing or recording Vigla? The public [creator
Kilbexllms.txtKilbex/Vigla/llms.txt
land in under two hours. Questions and bug-report routing: [SUPPORT.md](https://github.com/Kilbex/Vigla/blob/main/SUPPORT.md). Security reports: see [SECURITY.md](https://github.com/Kilbex/Vigla/blob/main/SECURITY.md). Reviewing or recording Vigla? The public [creator
EliasOulkadillms.txtEliasOulkadi/shokunin/llms.txt
PowerShell installation - [Install Guide (Unix)](install.sh): Unix shell installation - [Contributing](CONTRIBUTING.md): How to contribute - [Security](SECURITY.md): Security policy - [Code of Conduct](CODE_OF_CONDUCT.md): Community standards ## GitHub - https://github.com/eliasoulkadi/shokunin
EliasOulkadillms.txtEliasOulkadi/shokunin/.pack/llms.txt
Unix)](https://github.com/EliasOulkadi/shokunin/blob/main/install.sh): Unix shell installation - [Contributing](https://github.com/EliasOulkadi/shokunin/blob/main/CONTRIBUTING.md): How to contribute - [Security](https://github.com/EliasOulkadi/shokunin/blob/main/SECURITY.md): Security policy - [Code of Conduct](https://github.com/EliasOulkadi/shokunin/blob/main/CODE_OF_CONDUCT.md): Community standards ## GitHub
jklthinkingllms.txtjklthinking/retinue/docs/llms.txt
guide](https://github.com/jklthinking/retinue/blob/main/SELF_HOSTING.md): installation, upgrades, backup and restore drills, Docker Compose, exposure warnings. - [Security model](https://github.com/jklthinking/retinue/blob/main/docs/security.md): the untrusted-agent boundary, hook authority, holder-only writes, read-only
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.
