How real projects summarise themselves for language models.
vshulczllms.txtvshulcz/deja-vu/docs/llms.txt
what is read, what is redacted, what never leaves ## Optional - [Architecture](https://github.com/vshulcz/deja-vu/blob/main/docs/ARCHITECTURE.md) - [Security model](https://github.com/vshulcz/deja-vu/blob/main/docs/SECURITY-MODEL.md) - [Installing deja for an agent](https://github.com/vshulcz/deja-vu/blob/main/llms-install.md): the install page
hoangsonwwllms.txthoangsonww/Claude-Code-Agent-Monitor/llms.txt
source of truth for API contracts). - [Repository](https://github.com/hoangsonww/Claude-Code-Agent-Monitor): Source, issues, and discussions. - [security policy](https://github.com/hoangsonww/Claude-Code-Agent-Monitor/security/policy): Reporting vulnerabilities. - [LICENSE](https://raw.githubusercontent.com/hoangsonww/Claude-Code-Agent-Monitor/master/LICENSE): MIT license text
RyanAlbertsllms.txtRyanAlberts/best-of-Agent-Harnesses/llms.txt
# Best of Agent Harnesses > Hand-curated, ranked list of 167 AI agent harnesses — the
agentic-communityllms.txtagentic-community/mcp-gateway-registry/docs/llms.txt
enterprise-ready gateway and registry for Model Context Protocol (MCP) servers, enabling centralized management, secure access, and dynamic tool discovery for AI agents and development teams. The core goal
promptise-comllms.txtpromptise-com/Foundry/llms-full.txt
# Promptise Foundry — Complete Reference > Promptise Foundry is a Python framework for building production-grade
promptise-comllms.txtpromptise-com/Foundry/llms.txt
across 12 categories — adaptive, approval, hooks, mcp, memory, production, prompts, rag, reasoning, runtime, sandbox, security. All use real LLM calls via `build_agent()` (default model `openai:gpt-5-mini`). - [Changelog
sirkirbyllms.txtsirkirby/unifi-mcp/docs/llms.txt
github.com/sirkirby/unifi-mcp/blob/main/docs/permissions.md): Confirmation mode, bypass mode, and create, update, and delete policy controls. - [Security policy](https://github.com/sirkirby/unifi-mcp/blob/main/SECURITY.md): Supported reporting and security guidance. ## Architecture - [Architecture](https://github.com/sirkirby/unifi-mcp/blob/main/docs/ARCHITECTURE.md): Component responsibilities
santiferllms.txtsantifer/cv-santiago/public/llms.txt
person essay about building career-ops, evaluating 740 job listings, landing 12 interviews, and securing the Head of AI role. URL: https://www.businessinsider.com/how-i-built-tool-filter-job-listings-landed-head-ai-2026-4 - **Business Insider Deutschland** (German syndication
borgheillms.txtborghei/Claude-Skills/site/llms.txt
hiring, compensation, org structure, performance, and retention. Use when... - [Ciso Advisor](https://borghei.github.io/Claude-Skills/skills/c-level-advisor/ciso-advisor.html): Security leadership for growth-stage companies. Use when building security programs, selecting compliance frameworks... - [Cmo Advisor
duriantacollms.txtduriantaco/skylos/llms-full.txt
Skylos > Open-source AI code security and static analysis for Python, TypeScript, and Go. Skylos finds dead code, secrets, security vulnerabilities, and diff-aware regressions introduced during refactors
duriantacollms.txtduriantaco/skylos/llms.txt
Skylos > Open-source AI code security and static analysis tool for Python, TypeScript, and Go. Skylos finds dead code, secrets, security vulnerabilities, and diff-aware security regressions introduced during refactors
Scottcjnllms.txtScottcjn/Rustchain/llms.txt
Vintage System](https://github.com/Scottcjn/Rustchain/blob/main/CPU_ANTIQUITY_SYSTEM.md) - [Docker Deployment](https://github.com/Scottcjn/Rustchain/blob/main/DOCKER_DEPLOYMENT.md) - [Contributing](https://github.com/Scottcjn/Rustchain/blob/main/CONTRIBUTING.md) - [Security](https://github.com/Scottcjn/Rustchain/blob/main/SECURITY.md) - [Bounty Program](https://github.com/Scottcjn/rustchain-bounties)
Electricitysheepllms.txtElectricitysheep/dsh-handbook/llms-full.txt
Chinese, EN translations) covering install, profiles, plugin development, performance tuning, tools & context, MCP & subagents, security & sandbox, cache & cost engineering, ecosystem panorama. Includes same-model multi-agent benchmark (omp/dsh/opencode, 45/45), quickstart
Electricitysheepllms.txtElectricitysheep/dsh-handbook/llms.txt
Chinese, EN translations) covering install, profiles, plugin development, performance tuning, tools & context, MCP & subagents, security & sandbox, cache & cost engineering, ecosystem panorama. Includes same-model multi-agent benchmark (omp/dsh/opencode, 45/45), quickstart
aeonfunllms.txtaeonfun/aeon/llms.txt
Aeon works, strategy, voice/soul hierarchy, memory, tools, capability mode, skill chaining, notifications, network/secrets, security. - [CLAUDE.md](https://raw.githubusercontent.com/aeonfun/aeon/main/CLAUDE.md): The same operating manual, Claude Code loads it automatically. - [STRATEGY.md](https://raw.githubusercontent.com
qf-studiollms.txtqf-studio/pilot/llms.txt
fixes, small features, refactoring, tests, documentation, dependency updates. **Not Ideal For**: Large architectural changes, security-critical code, tasks requiring human judgment. ## Documentation - [README](https://github.com/qf-studio/pilot#readme): Full documentation, installation, configuration
h5i-devllms.txth5i-dev/h5i/docs/llms.txt
application from an attacker's perspective, so you do not need to be a security expert to start. The agent drives a browser session by id, reads the page
manojmallickllms.txtmanojmallick/sigmap/llms-full.txt
json) sigmap review-pr Audit a diff — scope drift, god-node edits, missing tests, security files (--staged, --base, --json, --markdown) sigmap review-pr --markdown PR Evidence Report — branded Markdown (signatures
emiliaprotocolllms.txtemiliaprotocol/emilia-protocol/public/llms-full.txt
rendered from checked-in evidence files, and CI fails a change that leaves the security case, the formal traces, the conformance manifest or this file out of date. ## Read This
emiliaprotocolllms.txtemiliaprotocol/emilia-protocol/public/llms.txt
constrain a path that bypasses the deployed enforcement point. ## Engineering Evidence EMILIA is implemented security infrastructure, not architecture-only: 10,870 automated tests across 657 files; 35 executable security claims
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.
