How real projects summarise themselves for language models.
Bande-a-Bonnotllms.txtBande-a-Bonnot/Boucle-framework/docs/llms.txt
home="$(mktemp -d)" tmp_project="$(mktemp -d)" cleanup() { if [ "${KEEP_BOUCLE_FIRST_TEST:-0}" != "1" ]; then rmdir "$tmp_home" "$tmp_project" 2>/dev/null || { printf 'Temporary directories were not empty; inspect
sandbaseaillms.txtsandbaseai/deepseek-harness-handbook/site/llms.txt
roots single-writer](https://sandbaseai.github.io/deepseek-harness-handbook/deepseek-harness-single-writer.html): Isolate concurrent Web, headless, ACP, SDK, service, and test processes or serialize shared-history ownership handoffs. - [Recover spawn ENOENT after a workspace moves
X-isdoingreatllms.txtX-isdoingreat/canvas-pilot/site/llms.txt
score. Opportunity analysis reads only sanitized policy facts and never starts an attempt to test them. - Conditional fit: accessible instructor sites, starter repositories, and configured APIs used to retrieve
pleaseaillms.txtpleaseai/shunt/llms.txt
Overview](./wiki/src/content/docs/01-getting-started/overview.md) - [Configuration](./wiki/src/content/docs/01-getting-started/configuration.md) - [Operations](./wiki/src/content/docs/01-getting-started/operations.md) ## Deep Dive - [Routing and Configuration](./wiki/src/content/docs/02-deep-dive/routing-and-configuration.md) - [Authentication](./wiki/src/content/docs/02-deep-dive/authentication.md) - [Testing and Quality](./wiki/src/content/docs/02-deep-dive/testing-and-quality.md
pleaseaillms.txtpleaseai/shunt/wiki/llms-full.txt
against the live xAI API — implemented from the reference clients (Hermes, OpenCode) and unit-tested with mocked endpoints only. ## Overview shunt ships a built-in `xai` provider that translates Anthropic
pleaseaillms.txtpleaseai/shunt/wiki/llms.txt
Translation](./src/content/docs/02-deep-dive/adapters-and-translation.md) — /02-deep-dive/adapters-and-translation - [Architecture](./src/content/docs/02-deep-dive/architecture.md) — /02-deep-dive/architecture - [Authentication](./src/content/docs/02-deep-dive/authentication.md) — /02-deep-dive/authentication - [Routing and Configuration](./src/content/docs/02-deep-dive/routing-and-configuration.md) — /02-deep-dive/routing-and-configuration - [Testing and Quality](./src/content/docs/02-deep-dive/testing-and-quality.md) — /02-deep-dive/testing-and-quality
Houseofmvpsllms.txtHouseofmvps/ultraship/llms.txt
enforces structured development workflows: brainstorming with spec approval, step-by-step implementation plans, test-driven development, systematic debugging, AI-powered code review, and a pre-deploy quality gate that scans
thebanrillms.txtthebanri/limoni/llms.txt
Limoni > Limoni is a terminal UI (TUI) engine for Go. Tests can click it, AI agents can drive it, and its render path makes no heap allocations. Module path: `github.com
agents-uillms.txtagents-ui/agents-kit/llms-full.txt
# Agents Kit 0.3.0 > React components for voice agents, conversations, generated results, and agent interactions
agents-uillms.txtagents-ui/agents-kit/llms.txt
task](https://agents-ui.github.io/agents-kit/c/ai-elements-task.json): task - [ai-elements-terminal](https://agents-ui.github.io/agents-kit/c/ai-elements-terminal.json): terminal - [ai-elements-test-results](https://agents-ui.github.io/agents-kit/c/ai-elements-test-results.json): test results - [ai-elements-tool](https://agents-ui.github.io/agents-kit/c/ai-elements-tool.json): tool - [ai-elements
future-agillms.txtfuture-agi/agent-learning-kit/docs/llms.txt
user behave as declared?](docs/simulate/persona-fidelity.md): twin=examples/sdk_persona_scenario_studio.py kind=agent-learning.persona-calibration.v1 - [Persona & Scenario Studio: typed test cases you can measure](docs/simulate/persona-scenario-studio.md): twin=examples/sdk_persona_scenario_studio.py kind=agent-learning.persona-library.v1 - [The Regression Lifecycle: baseline, compare
hermes-labs-aillms.txthermes-labs-ai/lintlang/llms-full.txt
Installers can download packages. Once dependencies are available, the scanner operates offline. Host-specific tested pins belong in their integration guides; they are not automatically interchangeable with the newest package
luongnv89llms.txtluongnv89/context-stats/docs/llms.txt
luongnv89.github.io/context-stats/troubleshooting.html): Common issues and solutions ## Development - [Development Guide](https://luongnv89.github.io/context-stats/DEVELOPMENT.html): Setup, testing, and contribution guide - [Deployment](https://luongnv89.github.io/context-stats/DEPLOYMENT.html): Release and deployment procedures ## Code - [GitHub Repository](https://github.com
Scottcjnllms.txtScottcjn/rustchain-mcp/llms.txt
FastMCP server and tool families. - `rustchain_mcp/rustchain_crypto.py` contains wallet cryptography and local keystore behavior. - `tests/` contains unit tests for wallet tools, discovery/actions, ecosystem tools, and mocks
yschimkellms.txtyschimke/compose-ai-tools/site/llms.txt
Agent workflows and the MCP tools for rendering, observing semantics, diffing previews, and generating tests. - [Render daemon](https://yschimke.github.io/compose-ai-tools/daemon/): Optional long-lived renderer for low-latency preview iteration
Kilbexllms.txtKilbex/Vigla/llms-full.txt
decides **Accept / Extend / Scrub / Escalate** — inside your envelope, without pinging you. Live state, diffs, tests, cost, and raw terminals are always one click away if you *want* to watch
Kilbexllms.txtKilbex/Vigla/llms.txt
decides **Accept / Extend / Scrub / Escalate** — inside your envelope, without pinging you. Live state, diffs, tests, cost, and raw terminals are always one click away if you *want* to watch
ZIZKA-AI-SLllms.txtZIZKA-AI-SL/ZizkaDB/llms.txt
overlay: `docker-compose.dev.yml`. ## Key context files - [CLAUDE.md](CLAUDE.md) — Full AI onboarding: stack, conventions, invariants, test commands - [Dashboard Knowledge Base](dashboard/DASHBOARD_KNOWLEDGE_BASE.md) — source of truth for the dashboard module (~1,100 lines) - [Architecture
EliasOulkadillms.txtEliasOulkadi/shokunin/llms.txt
craft, landing-craft, aesthetic-web, ui-ux-pro-max - **Mobile**: flutter, react-native - **Quality**: test-commander, performance-profiler, code-review - **Content**: content-marketing, translate-craft, communication, documentation - **Productivity**: git-workflow
EliasOulkadillms.txtEliasOulkadi/shokunin/.pack/llms.txt
craft, landing-craft, aesthetic-web, ui-ux-pro-max - **Mobile**: flutter, react-native - **Quality**: test-commander, performance-profiler, code-review - **Content**: content-marketing, translate-craft, communication, documentation - **Productivity**: git-workflow
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.
