How real projects summarise themselves for language models.
MarlinDiaryllms.txtMarlinDiary/worklouder-input-cli/llms.txt
independent microphone keys, persistent relay health/recovery, durable idempotency, and atomic multi-file gating. ## Core documentation - [README](https://github.com/MarlinDiary/worklouder-input-cli/blob/main/README.md): canonical project overview, status, scope, and core workflows - [Chinese README
mitos-runllms.txtmitos-run/mitos/llms.txt
value, ordering constraint, missing required field). Correct the value and resend; consult the endpoint documentation for the valid range and business rules. - `body_too_large` (HTTP 413): the body exceeds
ThreeMoonsLabllms.txtThreeMoonsLab/agents-shipgate/llms-full.txt
canonical agent-facing reference > material. AI search engines and coding agents that prefer one document > over chasing links should fetch this file. The short index is at > [`llms.txt`](llms.txt); machine
gizmaxllms.txtgizmax/Sandcastle/llms-full.txt
config: { output: markdown, pages: null, ocr: false, ocr_engine: auto }`. Extracts text/tables from a document. - sensor: `sensor_config: { url, condition: "status_code == 200", check_interval: 60, timeout: 86400, method, headers
gizmaxllms.txtgizmax/Sandcastle/site/llms-full.txt
config: { output: markdown, pages: null, ocr: false, ocr_engine: auto }`. Extracts text/tables from a document. - sensor: `sensor_config: { url, condition: "status_code == 200", check_interval: 60, timeout: 86400, method, headers
major7appsllms.txtmajor7apps/pensyve/llms.txt
endpoint: https://mcp.pensyve.com/mcp - REST API: https://api.pensyve.com - API keys: https://pensyve.com/settings/api-keys ## Documentation - [README](https://github.com/major7apps/pensyve/blob/main/README.md) — Overview, install, quickstart for all SDKs - [Architecture](https://github.com/major7apps/pensyve/blob/main/docs/ARCHITECTURE.md) — System design
AgriciDanielllms.txtAgriciDaniel/flow/llms-full.txt
internal links, proof, and conversion next steps. - Review the asset as an AI-readable document: clear headings, direct answers, concise tables where useful, source labels, and no hidden dependence
stabganllms.txtstabgan/openrouter-mcp-multimodal/llms.txt
search - `get_model_info` — pricing, context, modalities - `validate_model` — cheap model ID check - `rerank_documents` — OpenRouter `/rerank` - `health_check` — API key + reachability probe Errors: `_meta.code` — `INVALID_INPUT`, `UNSAFE_PATH`, `UPSTREAM
guardanallms.txtguardana/guardana/site/llms.txt
something, it says so and exits non-zero. This file is generated from the documentation map; do not edit it by hand. ## First run - [install.md](https://raw.githubusercontent.com/guardana/guardana/refs/heads/main/docs/install.md): install
AWSllms.txtaws/tools-for-devops-agent/llms.txt
path, flags non-deterministic selection, and produces describe/get/list validation commands grounded in public AWS documentation - [Bedrock Adoption Readiness Skill](skills/bedrock-adoption-readiness/SKILL.md): Assesses an AWS account's readiness to run Amazon Bedrock
jangtrinhllms.txtjangtrinh/design-os-3d-blender/docs/llms.txt
success, or `print('AGENT_FAIL: ')` on failure. Never evaluate success by process returncode alone. --- ## Documentation Links - [Project Landing](https://jangtrinh.github.io/design-os-3d-blender/): Overview of worked builds, verification contracts, and CLI commands
existential-birdsllms.txtexistential-birds/beagle/llms.txt
Beagle > Beagle is an Agent Skills marketplace: framework-aware code review, documentation, testing, architectural analysis, and git workflows for any compatible coding agent. It ships 10 plugins and 130+ skills
krzkollms.txtkrzko/google-cloud-mcp/llms-full.txt
Open-Source (FOSS)**: Permissive licensing allows modifications and custom app bundling. **Learn more:** * [TUUI document](https://www.tuui.com/) * [AIQL GitHub repository](https://github.com/AI-QL) ### Amazon Q CLI [Amazon
AuthPlanellms.txtAuthPlane/authserver/llms.txt
coding agents — SDK pins per stack, three byte-for-byte rules, retrofit recipe. - [Documentation index](docs/README.md): persona-shaped entry points (Evaluator / Builder / Operator / Architect / Contributor). ## Retrofit an existing MCP server
djadminllms.txtdjadmin/fort/landing/llms.txt
Links - Homepage: https://djadmin.github.io/fort/ - Source code (GitHub): https://github.com/djadmin/fort - Documentation / README: https://github.com/djadmin/fort/blob/main/README.md - Sample HTML report: https://djadmin.github.io/fort/sample-report.html - Releases: https://github.com/djadmin/fort/releases ## Common questions fort answers
sandraschillms.txtsandraschi/inkscape-mcp/llms-full.txt
combine`, `path_break_apart`, `object_to_path`, `optimize_svg`, `scour_svg`, `measure_object`, `query_document`, `count_nodes`, `export_dxf`, `layers_to_files`, `fit_canvas_to_drawing`, `render_preview`, `generate_laser
AsiaOstrichllms.txtAsiaOstrich/universal-dev-standards/llms.txt
selects into `.standards/` and writes instruction files for whichever AI tools that project uses. Documentation is licensed CC BY 4.0 and code MIT, so both are free to reuse. This
vitaecontextllms.txtvitaecontext/vitaecontext/llms-full.txt
metadata. - `src/` and `bin/`: CLI and stateless MCP server engine. - `mcp/`: Model Context Protocol documentation, configs, and schema contracts. ## 5. Skill behavior `SKILL.md` files define when a skill should
vitaecontextllms.txtvitaecontext/vitaecontext/llms.txt
prompts. - [Getting started](.assets/docs/getting-started.md): Human and agent onboarding path for choosing the right documentation branch. - [End-to-end demos](.assets/docs/end-to-end-workflows.md): Skill-ready agent workflows with sample inputs, prompts, multimodal material
HuckleR2003llms.txtHuckleR2003/PC_Workman_HCK/docs/llms-full.txt
test that the work happened. Includes a published correction: `psutil.sensors_temperatures()` is documented as available on Linux and FreeBSD only, so on Windows the attribute does not exist
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.
