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.
agentic-communityPipes a download into a shellllms.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
borgheiReads credentialsllms.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
sirkirbyllms.txtsirkirby/unifi-mcp/docs/llms.txt
command providers that keep passwords and API keys out of the client environment. - [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
Jarvis322Deletes or force-pushesllms.txtJarvis322/macos-sysdata/docs/llms-full.txt
macOS keeps them rather than the app: - **Full Disk Access**, in System Settings > Privacy & Security. Remove the entry with the **−** button. - **Notifications**, if you turned the low-space warning
basellms.txtbase/node-reth/llms-full.txt
Docker or snapshot local devnet, and the base-anvil GHCR package. - [SECURITY.md](SECURITY.md): Security policy: HackerOne and Cantina bug bounty programs, where to report offchain versus smart contract vulnerabilities
basellms.txtbase/node-reth/llms.txt
Docker or snapshot local devnet, and the base-anvil GHCR package. - [SECURITY.md](SECURITY.md): Security policy: HackerOne and Cantina bug bounty programs, where to report offchain versus smart contract vulnerabilities
pnpllms.txtpnp/powershell/pages/llms.txt
requires using your own Entra ID application registration for common interactive flows. - Respect security guidance in the authentication and permissions articles. Do not suggest hardcoded credentials, broad permissions, or legacy
promptise-comReads credentialsllms.txtpromptise-com/Foundry/llms-full.txt
systems. Build agents that discover tools, reason with custom patterns, remember context, enforce security, and run autonomously. ```bash pip install promptise ``` ## Quick Start ```python import asyncio from promptise import build
promptise-comReads credentialsllms.txtpromptise-com/Foundry/llms.txt
cutting behaviour with middleware. - [MCP Server Authentication: JWT and API Keys](https://docs.promptise.com/mcp/server/auth-security/): Secure an MCP server with JWT, asymmetric JWT, JWKS and API key auth, role and scope
kinopio-clubllms.txtkinopio-club/kinopio-client/public/llms.txt
Discord](https://kinopio.club/discord) - [Encryption](https://kinopio.club/help/encryption): Kinopio uses current best practices for securing your information, including encrypting data in-flight, salting/hashing user passwords, and not recording sensitive
h5i-devPipes a download into a shellllms.txth5i-dev/h5i/docs/llms.txt
into Lean 4. The h5i CLI provides project tooling, browser automation, HTTP inspection, reconnaissance, security regression testing, sandboxing, and a dashboard. Its security tools also work with existing apps that
hackclubllms.txthackclub/hcb/public/llms.txt
product changelog covering new features, infrastructure work, and technical deep-dives on payments, security, and nonprofit tooling. - [HCB is now open source](https://hackclub.com/fiscal-sponsorship/open-source/): March 2025 announcement post with
cryxnetReads credentialsllms.txtcryxnet/DeepMCPAgent/llms-full.txt
# Promptise Foundry — Complete Reference > Promptise Foundry is a Python framework for building production-grade
cryxnetllms.txtcryxnet/DeepMCPAgent/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
MetaMaskllms.txtMetaMask/metamask-docs/static/llms.txt
links for MetaMask Agent Wallet — the mm CLI for programmatic wallet access with mandatory security. - [Agent Wallet full documentation](https://docs.metamask.io/llms-agent-wallet-full.txt): Complete documentation for MetaMask Agent Wallet. ## Infura services
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
duriantacoReads credentialsllms.txtduriantaco/skylos/llms-full.txt
source (Apache-2.0), local-first static analysis CLI and pull-request gate: dead code, security issues, secrets, vulnerable dependencies, quality regressions and AI-code mistakes. ## Short answer Skylos
duriantacoReads credentialsllms.txtduriantaco/skylos/llms.txt
source (Apache-2.0), local-first static analysis CLI and pull-request gate: dead code, security issues, secrets, vulnerable dependencies, quality regressions and AI-code mistakes. ## Key facts - Skylos
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
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.
