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.
Googlellms.txtgoogle/three-live/examples/llms.txt
On-device JIT compiler and Web Components turning declarative HTML and AI-generated Three.js (<script type="text/three">) into WebGL2 & WebXR on the Web, Google Filament & Jetpack XR SceneCore on Android, and Apple RealityKit & Quick Look on iOS/visionOS.
NVIDIAllms.txtNVIDIA/go-dcgm/llms.txt
Rules for writing Go code that calls the go-dcgm bindings for NVIDIA Data Center GPU Manager (DCGM). This is a usage contract, not a repository map. Rules for changing this repository live in AGENTS.md. This file is for LLMs and agents writing programs that import github.com/NVIDIA/go-dcgm/pkg/dcgm, such as DCGM Exporter. The code in pkg/dcgm is the source of truth. The official DCGM documentation is authoritative for what a field or health system means. Do not invent functions, field IDs, status…
Continuellms.txtcontinuedev/amplified.dev/llms.txt
Every time a layer of the work became infrastructure, the role didn't shrink. The scope kept expanding. AI is the next layer in that pattern. Developers are not being automated. They are being amplified. This is an editorial essay that makes one argument: the anxiety developers feel about AI replacing them is real but misplaced. The historical pattern is consistent — memory management became a language feature, bare metal became the cloud, deployments became CI/CD. The work never disappeared. It…
AWSllms.txtaws/tools-for-devops-agent/llms.txt
Open-source tools for AWS DevOps Agent that extend its capabilities for incident response, root cause analysis, and operational troubleshooting. This repository contains skills, custom agents, and MCP servers that can be used with AWS DevOps Agent, as well as templates for writing your own. Skills follow the open Agent Skills specification; MCP servers follow the Model Context Protocol. This is the primary open-source collection of tools for AWS DevOps Agent — the AI-powered operations agent from AWS that automates incident…
Blockllms.txtblock/elasticgraph/config/site/src/llms-full.txt
{{ site.data.content.llm_content.content }}
Google Cloudllms.txtGoogleCloudPlatform/k8s-aibom/docs/llms.txt
An open-source (Apache-2.0), unprivileged Kubernetes controller that generates CycloneDX 1.6 ML-BOM documents for AI workloads at runtime — inference services, agent stacks, RAG pipelines, training jobs, and evaluation harnesses — with evidence locators and a confidence tier on every attribute.
Microsoftllms.txtmicrosoft/dotnet-modernization-for-beginners/llms.txt
A workshop about GitHub Copilot's .NET modernization tooling in Visual Studio. BookCatalog moves from .NET Framework 4.8 to .NET 10, followed by Azure planning. Read the reference guide first when applying this material to another application. The in-place rewrite, EF Core conversion, and disposable demo database are sample choices, not universal migration recommendations. The core Azure outcome is an assessment and reviewed plan, not deployment. These links serve plain Markdown without JavaScript at the course's public GitHub Pages address. This…
AWSllms.txtaws/aws-networking-best-practices/content/llms.txt
A reference architecture for AWS networking best practices, covering enterprise network design across five pillars: Foundation, Connectivity, Application Networking, Security, and Observability. This guide provides opinionated, production-ready networking guidance for AWS environments. It assumes multi-account AWS Organizations deployments, treats IPv6 as a core element, and includes cost implications in every architectural decision. Essential building blocks that everything else depends on. How AWS resources communicate with the internet, with each other, and with networks outside AWS. Traffic distribution, service discovery, and…
Microsoftllms.txtmicrosoft/Hybrid-Computer-Use/llms.txt
Hybrid Computer Use is an open-source MCP server, computer-use, that lets coding agents such as Codex, Claude Code, Gemini CLI and Grok Build operate Linux, macOS and Windows desktops. It adds two tools, AX (accessibility tree) and GUI (screenshots plus pointer and keyboard input), next to the agent's own shell and file tools, so the agent can mix code, accessibility and pixels in one task. Results reported in the paper (same model, harness, tasks and step budget; only the computer-use…
Microsoft Azurellms.txtAzure/kars/docs/llms.txt
kars is a secure, Kubernetes-native runtime for AI agents on Azure: one hardened sandbox per agent, zero credentials in the agent process, an in-pod inference router that brokers every external call, and an end-to-end encrypted inter-agent mesh. Governance is consumed from the Microsoft Agent Governance Toolkit (AGT). Source: https://github.com/Azure/kars (MIT). Docs are mdBook Markdown under docs/.
Microsoftllms.txtmicrosoft-foundry/forgebook/site/public/llms.txt
Microsoft Foundry cookbook of runnable Jupyter notebook recipes, hands-on AI guides, and examples for building agents, model inference, and multimodal apps. Forgebook recipes are authored as Jupyter notebooks and rendered as public recipe pages. For LLM context, prefer the Markdown recipe links below: they contain the notebook narrative and code in a compact text format without site navigation or client-side UI. Publishing is explicit. Notebook source files live in notebooks/, public metadata lives in registry.yaml, author profiles live in authors.yaml,…
Microsoftllms.txtmicrosoft/sqlsimtools/docs/llms.txt
Open-source load testing, benchmarking, and workload simulation tools for SQL Server 2019, 2022, and 2025, Azure SQL Database, Azure SQL Managed Instance, and SQL database in Microsoft Fabric. MIT licensed and community supported; not an official Microsoft product. sqlsimtools offers four ways to run the same kinds of SQL workloads: Every command must specify authentication: -E (Windows), -A (Microsoft Entra), -T <token> (access token), or -U/-P (SQL login). Results can be written as JSON with -json. Download releases from https://github.com/microsoft/sqlsimtools/releases/latest.
NVIDIAllms.txtNVIDIA/nv-sflow/docs-site/static/llms.txt
Declarative workflow descriptor (YAML) with swappable backends. Describe a workflow once — tasks, dependencies, resources, and launch methods — and run it on Slurm or locally (Docker and Kubernetes planned). sflow ships AI agent skills for writing and debugging sflow YAML, installable with sflow skill.
Microsoftllms.txtmicrosoft/Analytics-Hub/docs/community/learning-feed/llms.txt
A daily, deterministic feed of REAL changes to public Microsoft Copilot documentation (Microsoft Learn), the public Microsoft 365 Roadmap, and the public Microsoft 365 Message Center archive. changes lists only what actually moved since the prior scan (date bumps, silent edits, section add/remove, new pages, roadmap/MC status transitions), each with a machine-readable changeType. catalog lists the current state of every tracked page/item for grounding. Independent, community-run aggregation. NOT an official Microsoft notification service. Message Center content varies by tenant; roadmap…
Microsoftllms.txtmicrosoft/Analytics-Hub/docs/llms.txt
Open-source Power BI templates, exporters, apps, and add-ons from Microsoft's Copilot ROI Advisory Team for exploring Microsoft Copilot adoption, impact, consumption, sentiment, and readiness. The canonical source is https://microsoft.github.io/Analytics-Hub/ and https://github.com/microsoft/Analytics-Hub. A daily, machine-readable aggregation of factual changes to public Microsoft Copilot guidance (Microsoft Learn docs, the public Microsoft 365 Roadmap, and the public Message Center archive), classified by product and smart-tagged. Independent community aggregation, not an official Microsoft feed; each change links to its authoritative source, which is what…
JetBrainsllms.txtJetBrains/hexana/docs/llms.txt
Hexana is a WebAssembly and binary analysis toolkit by JetBrains, available as an IntelliJ Platform plugin (org.jetbrains.hexana) and a VS Code extension (JetBrains.hexana-wasm). It parses .wasm binaries (including extensionless ones…
Googlellms.txtgoogle/esmeralda/docs/src/llms.txt
Reference blueprint for running AI agents (Google ADK, A2A) and MCP tool servers in production on Google Cloud: a decoupled 6-layer Terragrunt/Terraform architecture (L0 CI/CD, L1 projects, L2 networking, L3 security & PKI, L4 governance with the Central Agent Gateway, L5 workloads) that enables multi-track parallelism across independent engineering teams. Agents run as BYOC images on Vertex AI Agent Engine with SPIFFE Agent Identity; private ingress flows through an internal HTTPS entry point (*.esmeralda.internal) with a built-in direct backend and…
Cloudflarellms.txtcloudflare/polystella/llms.txt
AI-driven content localization for Astro: build-time translation of Markdown/MDX/TOML/JSON/YAML into additional locales, cached in Cloudflare R2, with locale-prefixed routing. PolyStella is an Astro integration plus three published packages (core, EmDash, and Astro). Translations happen at build time, are content-addressed (source bytes + glossary + model), cached in R2, and rendered as static bytes — no runtime AI calls. The Astro package includes the integration and a polystella CLI with verb-style subcommands (translate, check-ui, sync-ui, translate-ui). Direct flow: source/record -> adapter…
Vercelllms.txtvercel-labs/arcade/apps/site/public/llms.txt
Arcade is an open-source TypeScript CPU 3D renderer, retained-mode terminal UI toolkit, and agent-playable game harness. Canonical site: https://ascii-arcade.dev Repository: https://github.com/vercel-labs/arcade Docs: https://ascii-arcade.dev/docs Using Arcade: https://ascii-arcade.dev/docs/app Controls and tutorial: https://ascii-arcade.dev/docs/app/controls Models, teams, and billing: https://ascii-arcade.dev/docs/app/models Browser integration: https://ascii-arcade.dev/docs/web Hosted CLI: https://ascii-arcade.dev/docs/browser-host HTTP interface: https://ascii-arcade.dev/openapi.json Capability status: https://ascii-arcade.dev/api/v1/status Use Arcade when you need CPU-rendered 3D graphics in a terminal or browser, retained terminal UI components, presentation-independent board-game rules, deterministic visual snapshots, or a persistent self-play harness for agent-driven games. Do not…
HashiCorpllms.txthashicorp/python-tfe/src/pytfe/llms.txt
Official Python SDK for the HCP Terraform and Terraform Enterprise (TFE) V2 API. A single TFEClient exposes ~70 resource namespaces (workspaces, runs, plans, applies, variables, teams, projects, policies, state versions,…
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.
