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.
garrytanllms.txtgarrytan/gstack/gstack/llms.txt
context saved earlier by /context-save. - [/context-save](context-save/SKILL.md): Save working context. - [/cso](cso/SKILL.md): Security audit: supported static findings; qualified profiles add reproduction and repair candidates. - [/design-consultation](design-consultation/SKILL.md
koala73llms.txtkoala73/worldmonitor/public/llms.txt
event score weights conflict at 30%, unrest at 25%, information signals at 25%, and security signals at 20%, then applies bounded boosts and authoritative floors. Each country has an instability
chopratejasllms.txtchopratejas/headroom/llms.txt
laptop, so it saves less than Headroom Enterprise. Enterprise adds more cost savings, tokens secured, on premise deployment, deep attribution and many more features. Teams and enterprises: contact hello@headroomlabs.ai
DeusDatallms.txtDeusData/codebase-memory-mcp/docs/llms.txt
research: https://github.com/DeusData/codebase-memory-mcp#performance - Benchmark report: https://github.com/DeusData/codebase-memory-mcp/blob/main/docs/BENCHMARK.md - Research paper: https://arxiv.org/abs/2603.27277 - Security and release verification: https://github.com/DeusData/codebase-memory-mcp#security
Steady21 mentions in 2 weeks
No other project uses it yet
tinyhumansaillms.txttinyhumansai/openhuman/llms.txt
tier together: a trusted local host request and an external channel message are different security contexts. `Access::full()` configures both access fields. A sandbox is an additional execution boundary, configured
Steady13 mentions in 2 weeks
No other project uses it yet
labstackllms.txtlabstack/echo/llms-full.txt
Redirect | HTTP redirect | | RequestID | Request ID header | | RequestLogger | Structured request logging | | Rewrite | URL rewriting | | Secure | Security headers | | Slash | Trailing slash handling | | Static | Static file serving | ## Wrapping stdlib handlers ```go echo.WrapHandler
No other project uses it yet
linera-iollms.txtlinera-io/linera-protocol/docs/llms.txt
linera.dev/developers/experimental/ml.html): Run ML models on the edge using the contract/service split for secure and efficient inference. - [Using EVM Smart Contracts on Linera](https://linera.dev/developers/experimental/ethereum.html): Run Ethereum Virtual Machine
No other project uses it yet
alirezarezvanillms.txtalirezarezvani/claude-skills/docs/llms-full.txt
handoff, andreessen ├── markdown-html/ # Markdown-to-interactive-HTML converter suite ├── standards/ # Communication, quality, git, security standards ├── templates/ # Reusable templates ├── docs/ # This MkDocs Material documentation site └── scripts/ # Build, sync, and validation
Steady17 mentions in 2 weeks
No other project uses it yet
alirezarezvanillms.txtalirezarezvani/claude-skills/docs/llms.txt
/claude-skills/commands/): The 102 slash commands. ## Domains - [Engineering — Core](https://alirezarezvani.github.io/claude-skills/skills/engineering-team/): Fullstack, AI/ML, DevOps, security, data, QA. - [Engineering — POWERFUL](https://alirezarezvani.github.io/claude-skills/skills/engineering/): Agent design, RAG, MCP, CI/CD, observability, SLOs, skill
Steady17 mentions in 2 weeks
5 projects use a version of this
bagistollms.txtbagisto/bagisto/public/llms.txt
/getting-started/why-choose-bagisto) - [Before You Start](/getting-started/before-you-start) - [Installation](/getting-started/installation) - [Upgrade Guide](/getting-started/upgrade-guide) - [Contribution Guide](/getting-started/contribution-guide) - [Best Security Practices](/getting-started/best-security-practice) - [Deployment](/getting-started/deployment) ### AI - [AI in Bagisto](/ai/introduction) - [Magic AI](/ai/magic-ai) - [Agent Skills](/ai/agent-skills
No other project uses it yet
a2aprojectllms.txta2aproject/A2A/docs/llms.txt
more) discover each other's capabilities, negotiate interaction modes, and collaborate on tasks securely without exposing internal state. ## Links - [Documentation home](https://a2a-protocol.org/latest/): Start here — overview, key features
No other project uses it yet
enescingozllms.txtenescingoz/awesome-n8n-templates/llms.txt
store integration. - [Slack](https://github.com/enescingoz/awesome-n8n-templates/tree/main/Slack): 9 templates for AI bots, customer support ticketing, security operations, sentiment analysis, and information monitoring. - [OpenAI and LLMs](https://github.com/enescingoz/awesome-n8n-templates/tree/main/OpenAI_and_LLMs): 17+ templates
No other project uses it yet
NirDiamantllms.txtNirDiamant/agents-towards-production/llms.txt
independent tutorial tracks, each covering one layer of the production stack: orchestration, memory, retrieval, security and guardrails, observability and tracing, evaluation, deployment, GPU serving, fine-tuning and user interfaces. Each
Evil0ctalllms.txtEvil0ctal/Douyin_TikTok_Download_API/llms.txt
configuration layers and all 65 settings, with defaults and when to change them. - [Security](https://github.com/Evil0ctal/Douyin_TikTok_Download_API/blob/main/documents/en/15-security.md): What the instance protects, what you are responsible for, and what
corsairdevllms.txtcorsairdev/corsair/docs/llms.txt
with OAuth 2.0 flows. - [OAuth process](https://docs.corsair.dev/concepts/oauth-process.md): A production OAuth implementation with security best practices. ## Hub Optional hosted relay for the parts of Corsair that need a public
OpenNHPllms.txtOpenNHP/opennhp/docs/llms.txt
endcomment %}# OpenNHP > OpenNHP is the open-source reference implementation of the Cloud Security Alliance > (CSA) Network-infrastructure Hiding Protocol (NHP) specification. It enforces > Zero Trust at the OSI session layer
No other project uses it yet
NangoHQllms.txtNangoHQ/nango/docs/llms.txt
environments - [Platform: Limits](https://nango.dev/docs/guides/platform/limits.md): Overview of resource limits on Nango Cloud. - [Platform: Security](https://nango.dev/docs/guides/platform/security.md): How Nango secures your API credentials and customer data. - [Platform: Audit trail
phpllms.txtphp/frankenphp/llms.txt
state machine, the Go/C/PHP CGO boundary, auto-scaling, and per-thread environment sandboxing. - [FrankenPHP Security Model](https://frankenphp.dev/docs/security/): trust boundaries between Go, C, and PHP (which inputs are untrusted
Steady8 mentions in 2 weeks
No other project uses it yet
replicatellms.txtreplicate/cog/docs/llms.txt
# Cog: Containers for machine learning Cog is an open-source tool that lets you
No other project uses it yet
chaitanyagirillms.txtchaitanyagiri/munder-difflin/docs/llms.txt
your hive runs on your plan as before. - [MCP Tool Poisoning: How to Secure the Model Context Protocol](https://munderdiffl.in/blog/mcp-security-tool-poisoning/): How the Model Context Protocol gets attacked — tool poisoning
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.
