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.
tecnologicachilePipes a download into a shellllms.txttecnologicachile/mail-mcp/site/llms-full.txt
SMTP_DEFAULT_USER": "you@gmail.com", "MAIL_SMTP_DEFAULT_PASS": "your-app-password", "MAIL_SMTP_DEFAULT_SECURE": "starttls", "MAIL_IMAP_WRITE_ENABLED": "true", "MAIL_SMTP_WRITE_ENABLED": "true" } } } } ``` For Microsoft
tecnologicachilePipes a download into a shellllms.txttecnologicachile/mail-mcp/site/llms.txt
setup](https://raw.githubusercontent.com/tecnologicachile/mail-mcp/main/docs/account-setup.md): Gmail, Microsoft 365, Outlook.com (EWS/Graph device code flow), iCloud, Zoho - [Security](https://raw.githubusercontent.com/tecnologicachile/mail-mcp/main/docs/security.md): write gating, secret handling, attachment confinement - [Advanced configuration](https://raw.githubusercontent.com/tecnologicachile/mail-mcp/main/docs/advanced-configuration.md): timeouts
hogancvllms.txthogancv/coordinate-agents/docs/llms.txt
hogancv.github.io/coordinate-agents/install-with-ai.html Troubleshooting: https://hogancv.github.io/coordinate-agents/troubleshooting.html FAQ: https://hogancv.github.io/coordinate-agents/faq.html Comparison: https://hogancv.github.io/coordinate-agents/comparison.html Security: https://hogancv.github.io/coordinate-agents/security.html Simplified Chinese: https://hogancv.github.io/coordinate-agents/zh-CN/ ## v2.4 historical documentation and migration v2.4 already
UmairReads credentialsllms.txtUmair/stalemap/site/llms-full.txt
Copyright Umair Ejaz and stalemap contributors. - Issues and contributions: https://github.com/Umair/stalemap (see CONTRIBUTING.md). Security reports: private vulnerability reporting on GitHub (see SECURITY.md). - Not affiliated with Anthropic or any library
Umairllms.txtUmair/stalemap/site/llms.txt
Example notes block](https://github.com/Umair/stalemap/blob/main/examples/next-ai-app.claude-sonnet-4-5.md): real output for a Next.js + AI SDK app - [Security policy](https://github.com/Umair/stalemap/blob/main/SECURITY.md): reporting vulnerabilities, scope ## Benchmark - [Held-out v4 protocol](https://github.com/Umair/stalemap/blob/main/bench/heldout-v4/PROTOCOL.md):
Apra-LabsReads credentialsllms.txtApra-Labs/apra-fleet/llms-full.txt
/badge/License-Apache_2.0-blue.svg)](https://opensource.org/licenses/Apache-2.0) [](https://github.com/Apra-Labs/apra-fleet/releases) [](https://modelcontextprotocol.io) [](https://deepwiki.com/Apra-Labs/apra-fleet) [](https://www.skillsdirectory.com/skills/apra-labs-apra-fleet) [Quick Start](#quick-start-5-minutes) - [Live Demo](#watch
Apra-Labsllms.txtApra-Labs/apra-fleet/llms.txt
Setup](docs/ssh-setup.md): Enabling SSH access on a remote machine. - [Out-of-Band Auth](docs/features/oob-auth.md): Securely managing credentials and passwords for fleet members. - [Git Authentication](docs/design-git-auth.md): How git authentication works across
raphaelmansuyllms.txtraphaelmansuy/adk_training/docs/llms.txt
raphaelmansuy.github.io/adk_training/docs/advanced_observability)** - Production monitoring, logging, and performance optimization - **[25: Best Practices](https://raphaelmansuy.github.io/adk_training/docs/best_practices)** - Security, performance, and maintainability patterns - **[26: Google Agentspace](https://raphaelmansuy.github.io/adk_training/docs/google_agentspace)** - Enterprise agent management and collaboration
NARUBROWNllms.txtNARUBROWN/spine/llms.txt
right reference first | Goal | Reference | Start with | |---|---|---| | Learn the current minimal runtime and secure defaults | This repository | `cmd/demo`, `examples/security-config`, `test/app_integration_test.go` | | Scaffold a project, inspect execution contracts, or generate OpenAPI/AsyncAPI | [spine
tenuo-aillms.txttenuo-ai/tenuo/docs/llms.txt
tenuo.ai/api-reference): Python SDK reference - [Debugging Guide](https://tenuo.ai/debugging): Troubleshoot authorization failures - [Security](https://tenuo.ai/security): Threat model, PoP, integration safety, and best practices - [Compatibility Matrix](https://tenuo.ai/compatibility-matrix):
stabganReads credentialsllms.txtstabgan/openrouter-mcp-multimodal/llms.txt
IMAGE_INLINE_MAX_BYTES`, `OPENROUTER_AUDIO_INLINE_MAX_BYTES`, `OPENROUTER_VIDEO_INLINE_MAX_BYTES`. ## Security - Input/output path sandboxes (`OPENROUTER_INPUT_DIR`, `OPENROUTER_OUTPUT_DIR`); bypass `OPENROUTER_ALLOW_UNSAFE_PATHS
MarcoPorcellatoReads credentialsllms.txtMarcoPorcellato/matryca-plumber/llms.txt
aliases like `[42]` without a page still fail with `ok: false`. Spec: `docs/openspec/agent-ax-robustness.md` ### 2.4 Security & Sandbox (v1.9.9+) Graph reads and writes stay inside **`LOGSEQ_GRAPH_PATH`**. v1.9.9 adds defense
Arthurdwllms.txtArthurdw/rovo/llms-full.txt
span several lines. The status must also appear in `# Responses`. - `# Metadata`: `@tag ` (repeatable), `@security ` (repeatable; the scheme must be registered in `api.components.security_schemes`), `@id ` (alphanumerics and `_` only; defaults
Arthurdwllms.txtArthurdw/rovo/llms.txt
span several lines. The status must also appear in `# Responses`. - `# Metadata`: `@tag ` (repeatable), `@security ` (repeatable; the scheme must be registered in `api.components.security_schemes`), `@id ` (alphanumerics and `_` only; defaults
permawebReads credentialsllms.txtpermaweb/HyperBEAM/docs/llms-full.txt
gain high confidence that the computation was performed correctly and confidentially within the secure environment, untampered by the node operator. **Obtaining Attested Responses:** This usually involves interacting with nodes specifically
2389-researchllms.txt2389-research/claude-plugins/docs/llms.txt
truth - [fresh-eyes-review](https://skills.2389.ai/plugins/fresh-eyes-review/): Mandatory final sanity check before commits/PRs - catches security vulnerabilities, logic errors, and bugs that slip through tests - [documentation-audit](https://skills.2389.ai/plugins/documentation-audit/): Verify
backenlyllms.txtbackenly/backenly/public/llms.txt
list of problems on its own (a missing index, a table without row-level security, a missing realtime trigger), verifying each fix. Anything else becomes a finding with evidence
trahloffllms.txttrahloff/Aldine/site/llms.txt
notes](https://raw.githubusercontent.com/trahloff/Aldine/main/docs/SCALING.md): architecture, what scales and what is single-node by design - [Security policy](https://raw.githubusercontent.com/trahloff/Aldine/main/SECURITY.md): threat model, sandbox details, reporting - [Contributing](https://raw.githubusercontent.com/trahloff/Aldine/main/CONTRIBUTING.md): dev setup
runxhqllms.txtrunxhq/runx/llms.txt
docs/publishing.md) - [Releasing](docs/releasing.md) - [Operator Console](docs/operator-console.md) - [Skill Author Runtime Contract](docs/skill-author-runtime-contract.md) - [Skill Catalog](docs/skill-catalog.md) - [Security Authority Proof](docs/security-authority-proof.md) - [Runx System Architecture](docs/architecture/runx-system.md) - [Act Model](docs/act-model.md) - [How We Test](docs/how-we-test.md) ## Examples
bestagentkitsllms.txtbestagentkits/cloud-harness-mcp/site/llms.txt
page. - [Getting started](https://docs.harness.agentkit.best/getting-started.md): Open a workspace and run the first commands. - [Security model](https://docs.harness.agentkit.best/security-model.md): Threat model, network isolation, and credential boundaries. ## Source - [GitHub repository
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.
