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.
langroidReads credentialsllms.txtlangroid/langroid/llms.txt
that this file may contain sensitive information. Handle it with the same level of security as you would the original repository. - Pay special attention to the Repository Description. These contain
No other project uses it yet
zhw2590582Reads credentialsllms.txtzhw2590582/ArtPlayer/docs/llms.txt
===== Documentation Summary ===== Advanced Properties The Advanced Properties refer to the secondary properties attached to
No other project uses it yet
yvgudellms.txtyvgude/lean-ctx/llms.txt
report .` and report the methodology. - [Changelog](https://github.com/yvgude/lean-ctx/blob/main/CHANGELOG.md): release history (Keep a Changelog). - [Security](https://github.com/yvgude/lean-ctx/blob/main/SECURITY.md): hardening and disclosure policy. - [Community and commercial options](https://leanctx.com/pricing/): edition
Steady4 mentions in 2 weeks
No other project uses it yet
cosmicstack-labsPipes a download into a shellllms.txtcosmicstack-labs/mercury-agent/docs/llms-full.txt
Safest, Most Secure, and Permission-Aware AI Agents for Real-World Tasks > Grok, ChatGPT Work, Mercury, OpenClaw, Manus, Gemini agent for work, Devin, Claude Cowork and Comet compared on memory
No other project uses it yet
cosmicstack-labsPipes a download into a shellllms.txtcosmicstack-labs/mercury-agent/docs/llms.txt
Updating Mercury](https://mercuryagent.sh/docs/desktop/updating): desktop and server updates, rollback, required updates - [Remote access & security](https://mercuryagent.sh/docs/desktop/remote-access): owner approvals, device tokens, /server - [CLI commands](https://mercuryagent.sh/docs/cli-commands/cli-commands): every `mercury
No other project uses it yet
ascending-llcReads credentialsllms.txtascending-llc/jarvis-registry/docs/llms-full.txt
hardest problems in enterprise AI: giving AI chatbots, copilots, developer IDEs, and autonomous agents **secure, governed access** to internal tools, data, and approved skills — without fragmented integrations or security blind
No other project uses it yet
ascending-llcllms.txtascending-llc/jarvis-registry/docs/llms.txt
control plane for AI — connecting copilots, autonomous agents, and enterprise tools through a single, secure, and observable gateway. It handles both MCP (Model Context Protocol) servers and A2A agents
No other project uses it yet
erigontechReads credentialsllms.txterigontech/erigon/llms-full.txt
# Introduction URL: https://docs.erigon.tech/ An efficient, modular Ethereum execution layer client built for performance
No other project uses it yet
erigontechllms.txterigontech/erigon/llms.txt
Logs](https://docs.erigon.tech/fundamentals/logs): Log levels, structured logging, and how to interpret Erigon output. - [Security](https://docs.erigon.tech/fundamentals/security): Firewall rules, API exposure best practices, and hardening recommendations. - [JWT Secret
No other project uses it yet
PurpleDoubleDllms.txtPurpleDoubleD/locally-uncensored/docs/llms-full.txt
cannot be confirmed by voice. Terminals, password managers, system sign-in and permission dialogs, security settings, the Run dialog and windows with administrator rights are always off limits
No other project uses it yet
PurpleDoubleDllms.txtPurpleDoubleD/locally-uncensored/docs/llms.txt
list of apps that are off limits (terminals, password managers, system sign-in and security dialogs). - Dictation (Whisper) and read aloud (Piper) - Auto-update over signed NSIS channel for Windows
No other project uses it yet
Microsoftllms.txtmicrosoft/agent-skills/docs/llms-full.txt
models](https://learn.microsoft.com/en-us/azure/ai-foundry/control-plane/quickstart-create-guardrail-policy?view=foundry) - [Optimize cost and performance](https://learn.microsoft.com/en-us/azure/ai-foundry/control-plane/how-to-optimize-cost-performance?view=foundry) - [Manage compliance and security](https://learn.microsoft.com/en-us/azure/ai-foundry/control-plane/how-to-manage-compliance-security?view=foundry) - [Configure an AI gateway](https://learn.microsoft.com/en-us/azure/ai-foundry/configuration/enable-ai-api-management-gateway-portal?view=foundry) ## Observability, evaluation, & tracing - [Observability overview
2 projects use a version of this
Microsoftllms.txtmicrosoft/agent-skills/docs/llms.txt
models](https://learn.microsoft.com/en-us/azure/ai-foundry/control-plane/quickstart-create-guardrail-policy?view=foundry) - [Optimize cost and performance](https://learn.microsoft.com/en-us/azure/ai-foundry/control-plane/how-to-optimize-cost-performance?view=foundry) - [Manage compliance and security](https://learn.microsoft.com/en-us/azure/ai-foundry/control-plane/how-to-manage-compliance-security?view=foundry) - [Configure an AI gateway](https://learn.microsoft.com/en-us/azure/ai-foundry/configuration/enable-ai-api-management-gateway-portal?view=foundry) ## Observability, evaluation, & tracing - [Observability overview
2 projects use a version of this
mengjian-githubllms.txtmengjian-github/openclaw101/public/llms-full.txt
browsing (real Chrome via Browser Relay), file management, and more. OAuth setup guides and security best practices included. ### Day 5: Skills Ecosystem URL: https://openclaw101.dev/day/5 Skills are plugins that
No other project uses it yet
CanineHQllms.txtCanineHQ/canine/public/llms.txt
cert-manager - Resource constraints: CPU, memory, and GPU limits per service - Environment variables: Secure config management per project - Metrics & monitoring: Cluster and project-level resource metrics - Teams & RBAC: Team-based
No other project uses it yet
loomioReads credentialsllms.txtloomio/loomio/public/llms.txt
documentation as the authority for authentication, permissions, parameters, request behaviour and response formats. ## Security Never include API keys in URLs. Send credentials only in the `Authorization` header. Do not assume
No other project uses it yet
ntex-rsllms.txtntex-rs/ntex/docs/llms.txt
keep protocol code independent of TLS backends. - HTTP clients use `openssl`, `rustls`, or `secure_connector` for HTTPS; `ClientBuilder::connector` configures unsecured connections. Supply verifying TLS configurations explicitly: the built
Steady6 mentions in 2 weeks
No other project uses it yet
quantizorllms.txtquantizor/markdown-to-jsx/docs/llms.txt
included, gets its attributes as written text (`data={[1, 2]}` arrives as `"{[1, 2]}"`). ## Security Raw HTML is sanitized in every renderer, always, independent of `options.sanitizer`. Stripped before render: every
No other project uses it yet
Metallms.txtfacebookresearch/fairchem/docs/llms-full.txt
# FAIR Chemistry: Complete Documentation Canonical site: https://facebookresearch.github.io/fairchem/ --- Source: `docs/index.md` +++ {"class": "col-page
Steady4 mentions in 2 weeks
No other project uses it yet
Jieyab89llms.txtJieyab89/OSINT-Cheat-sheet/llms.txt
young professional passionate about IT — programming, OSINT for military and journalism applications, and IT security including operating systems and penetration testing. Active in the field for over three years
No other project uses it yet
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.
