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.
LangChainllms.txtlangchain-ai/langchain-aws/llms.txt
Code Interpreter](https://python.langchain.com/docs/integrations/tools/bedrock_agentcore_code_interpreter/): Documentation for executing Python, JavaScript, and TypeScript code in secure AgentCore sandbox environments. Covers code execution, file operations, and package installation. - [Amazon Bedrock AgentCore Memory
SirAllapllms.txtSirAllap/agentglass/landing/llms.txt
raw.githubusercontent.com/SirAllap/agentglass/main/docs/CONFIG.md): every environment variable the code reads, the whole HTTP API, the architecture - [Security](https://raw.githubusercontent.com/SirAllap/agentglass/main/SECURITY.md): the trust model, what each surface can reach, retention, how to report
baseReads credentialsllms.txtbase/docs/docs/llms-full.txt
stock token for illustration; the same flows apply to other asset types. Tokenized securities examples shown for illustration. Base is a general-purpose blockchain; issuance and compliance are the responsibility
basellms.txtbase/docs/docs/llms.txt
covers details of the two-component cost system involving L2 execution fees and L1 security fees, and offers insights on fee variations and cost-saving strategies. - [Throughput and Limits
raysonmengPipes a download into a shellllms.txtraysonmeng/agent-bridge/site/llms.txt
tenant system. - Not a generic orchestration framework for arbitrary agent backends. - Not a hardened security boundary between tools you do not trust. ## Three core benefits - Cross-review, not just cross
alexsergivanllms.txtalexsergivan/kwant/site/llms.txt
commercial license, privacy requests or press. Bugs and ideas go to GitHub issues, security problems to a private GitHub report. - [Features: self-hosted AI agent orchestration](https://kwant.si/features): Teams
claude-did-thisPipes a download into a shellllms.txtclaude-did-this/MCPControl/docs/llms-full.txt
Tool integration for executing commands and scripts * Local server connections for enhanced privacy and security > ? Note: The Claude.ai web application does not currently support MCP. MCP features are only available
canonicalllms.txtcanonical/ubuntu.com/templates/llms-full.txt
cloud, to containers and IoT devices. Ubuntu LTS releases receive five years of free security updates, extendable to up to 15 years with Ubuntu Pro. --- ## About Ubuntu ### About Ubuntu Ubuntu
canonicalllms.txtcanonical/ubuntu.com/templates/llms.txt
cloud, to containers and IoT devices. Ubuntu LTS releases receive five years of free security updates, extendable to up to 15 years with Ubuntu Pro. ## Main pages - [About Ubuntu
SveltyCMSReads credentialsllms.txtSveltyCMS/SveltyCMS/static/llms.txt
Real-Time Updates](https://docs.sveltycms.com/docs/reference/api/graphql-subscriptions): Server-Sent Events (SSE) and Yjs CRDT collaboration. - [Security Architecture](https://docs.sveltycms.com/docs/reference/security): CSP, field-level access control, and Passkeys/WebAuthn. - [Database Adapters](https://docs.sveltycms.com
fjrevoredollms.txtfjrevoredo/mini-diarium/website/llms-full.txt
unlock without typing your password. You can also enable **idle auto-lock** in **Preferences → Security → Auto-Lock**. When enabled, Fenmark locks automatically after the configured period of inactivity. ## Multiple Journals
fjrevoredollms.txtfjrevoredo/mini-diarium/website/llms.txt
feed: https://fenmark.app/blog/feed.xml - Source code: https://github.com/fjrevoredo/mini-diarium - License: MIT (https://opensource.org/licenses/MIT) - Security policy: https://github.com/fjrevoredo/mini-diarium/blob/master/SECURITY.md - Privacy policy: https://github.com/fjrevoredo/mini-diarium/blob/master/docs/PRIVACY.md - AI crawler policy: https://fenmark.app/ai-crawlers.txt
iternal-technologies-partnersllms.txtiternal-technologies-partners/blockify-agentic-data-optimization/llms.txt
ELSER + dense retrieval on deduplicated IdeaBlocks. - [Blockify + Supabase](documentation/integrations/BLOCKIFY-SUPABASE.md): Postgres + pgvector with row-level security on IdeaBlock tags. - [Blockify + Starburst](documentation/integrations/BLOCKIFY-STARBURST.md): Federated IdeaBlock generation across data-lake catalogs (Trino + Iceberg
stevezauReads credentialsllms.txtstevezau/plex_generate_vid_previews/docs/llms-full.txt
token 3. Follow the wizard. Its steps are **Server type**, **Connect**, **Paths**, **Options** and **Security**: - **Step 1 — Choose your media server**: click **Plex**, **Emby** or **Jellyfin**. - **Plex** → **Sign in with
tawrootPipes a download into a shellllms.txttawroot/antigravity-cleaner/website/llms.txt
РФ)](https://tawroot.github.io/antigravity-cleaner/blog-google-antigravity-russia-403.html) - [Full Troubleshooting & Diagnostic Matrix](https://tawroot.github.io/antigravity-cleaner/troubleshooting.html) - [Frequently Asked Questions & Security FAQ](https://tawroot.github.io/antigravity-cleaner/faq.html) - **License**: Apache-2.0 (100% auditable, offline, zero-telemetry) - **Supported Platforms**: Linux
SonarSourcePipes a download into a shellllms.txtSonarSource/sonarqube-cli/docs/llms.txt
SonarQube CLI > Code quality and security in your terminal. Scan, integrate, and fix issues — locally or with AI. - Version: 1.11.0 - Install (Linux/macOS): curl -o- https://raw.githubusercontent.com/SonarSource/sonarqube-cli/refs/heads/master/user-scripts/install.sh | bash - Install (Windows
gosudaPipes a download into a shellllms.txtgosuda/portal/llms.txt
operate a relay. - [API reference](https://raw.githubusercontent.com/gosuda/portal-tunnel/main/docs/src/routes/api-reference/+page.md): Relay HTTP endpoints and shared types. - [Security model](https://raw.githubusercontent.com/gosuda/portal-tunnel/main/docs/src/routes/security-model/+page.md): Encryption and trust boundaries. - [Application access authentication](https://raw.githubusercontent.com/gosuda/portal-tunnel/main/docs/src/routes/siwe-authentication/+page.md): Limit
gosudaPipes a download into a shellllms.txtgosuda/portal-tunnel/llms.txt
operate a relay. - [API reference](https://raw.githubusercontent.com/gosuda/portal-tunnel/main/docs/src/routes/api-reference/+page.md): Relay HTTP endpoints and shared types. - [Security model](https://raw.githubusercontent.com/gosuda/portal-tunnel/main/docs/src/routes/security-model/+page.md): Encryption and trust boundaries. - [Application access authentication](https://raw.githubusercontent.com/gosuda/portal-tunnel/main/docs/src/routes/siwe-authentication/+page.md): Limit
Pangu-Immortalllms.txtPangu-Immortal/KeepLiveService/llms-full.txt
Force-stop sets `FLAG_STOPPED`, disabling all static broadcast receivers. This is an Android security mechanism. Enable `ForceStopResistance` (disabled by default) for the 5ms race-condition technique using Native
grisunollms.txtgrisuno/LazyOwn/readmenator-maps/llms.txt
stars](https://github.com/grisuno/LazyOwn/stargazers) - [SECURITY.md](md/SECURITY.md): The following LazyOwn versions currently receive support and security updates: ## Optional - [Runtime Architecture](architecture.html): Components, services, storage, and boundaries across layers. (interactive HTML) - [Data
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.
