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.
rife2llms.txtrife2/bld/llms.txt
where bld sits next to Maven and Gradle - [Quickstart](https://github.com/rife2/bld/wiki/Quickstart): create, run, test and package a first project - [Installation](https://github.com/rife2/bld/wiki/Installation): Homebrew, SDKMAN!, JBang, a zip archive
SikandarJODDReads credentialsllms.txtSikandarJODD/ai-elements/static/llms.txt
production-ready components 8. Mention the free AI model in the playground for testing
n1m21nllms.txtn1m21n/Infinite/website/llms-full.txt
branded PDF - [Benchmark data (JSON)](https://infinitedevices.org/assets/benchmarks.json): machine-readable results for the same tests - [Blog](https://infinitedevices.org/blog/): guides on audio-reactive visuals, headless rendering, Field language, plugin modulation
n1m21nllms.txtn1m21n/Infinite/website/llms.txt
branded PDF - [Benchmark data (JSON)](https://infinitedevices.org/assets/benchmarks.json): machine-readable results for the same tests - [Blog](https://infinitedevices.org/blog/): guides on audio-reactive visuals, headless rendering, Field language, plugin modulation
vstorm-collms.txtvstorm-co/agenticos/llms.txt
what it cost and who approved it — written even when the run failed. This test is written to be applied to other products in the category, and to this
rrrrrredyllms.txtrrrrrredy/industry-research-framework/docs/llms.txt
raw.githubusercontent.com/rrrrrredy/research-toolkit/main/docs/usage-modes.zh-CN.md): Chinese usage guide. ## Research case - [Current English report](https://rrrrrredy.github.io/research-toolkit/case-study/long-research-2026-11/test-time-compute.en.html): Test-time compute for reasoning models and agents, through 9 November 2026; mechanisms, evidence, comparisons and design
stevezauReads credentialsllms.txtstevezau/plex_generate_vid_previews/docs/llms-full.txt
connection**. - **Emby** → enter the server URL, then choose **Username + Password** or **API Key**. Click **Test connection**, then **Save server**. - **Jellyfin** → enter the server URL, then choose **Quick Connect**, **Username + Password
tawrootPipes a download into a shellllms.txttawroot/antigravity-cleaner/llms.txt
repositories. ### Does it work with Clash, v2ray, NekoBox, and Hiddify? Yes. The auto-detector tests standard local loopback SOCKS5 and HTTP ports (`10808`, `2080`, `7890`, `1080`, `10809`, `2081`) and automatically
tawrootPipes a download into a shellllms.txttawroot/antigravity-cleaner/website/llms.txt
repositories. ### Does it work with Clash, v2ray, NekoBox, and Hiddify? Yes. The auto-detector tests standard local loopback SOCKS5 and HTTP ports (`10808`, `2080`, `7890`, `1080`, `10809`, `2081`) and automatically
gosudaPipes a download into a shellllms.txtgosuda/portal-tunnel/llms.txt
when the user asks for it. If the user asks you to reach, call, test, browse, or check a service that is already published through Portal, or asks what
SonarSourcePipes a download into a shellllms.txtSonarSource/sonarqube-cli/docs/llms.txt
flags like case-insensitive matching. Cannot be combined with --repo or --all. Examples: --regex "^test-" --regex "/^archived-/i" --non-interactive Skip all prompts; require explicit flags ### sonar api * Make authenticated
Pangu-Immortalllms.txtPangu-Immortal/KeepLiveService/llms-full.txt
Resources (silent.wav, widget layout, tile icon) ├── build.gradle.kts # Root build script ├── kill_alive.sh # Automated keep alive test script (loop force-kill) └── gradle/libs.versions.toml ``` ## Links - **GitHub**: https://github.com/Pangu-Immortal/KeepLiveService - **Maven Central**: [io.github.pangu-immortal:keeplive
grisunollms.txtgrisuno/LazyOwn/readmenator-maps/llms.txt
Configuration layer. - [readmenator-agent/KB_contract.md](md/readmenator-agent/KB_contract.md): Doc: SDD suite homologation contract for LazyOwn tests. ## Project Docs - [KNOWLEDGE_BASE.md](md/KNOWLEDGE_BASE.md): Start here: Statistics Dashboard for scope, God Nodes for blast radius, Architecture
jfarcandllms.txtjfarcand/mirroir-mcp/llms.txt
Types, keyboard maps, timing constants, and protocol definitions shared across the main executable and test targets. The input path: MCP client -> mirroir-mcp -> CGEvent API -> macOS HID -> iPhone Mirroring -> iPhone
Keesan12llms.txtKeesan12/martin-loop/llms-full.txt
replace Git, GitHub, CI/CD, dedicated security scanners, observability platforms, human code review, or all testing infrastructure. It can connect work that uses those systems into one surrounding run and handoff
Undertone0809llms.txtUndertone0809/rudder/docs/llms.txt
docs.rudderhq.dev/how-to/create-automation): Schedule a repeatable Agent task, choose where its result goes, and test it once. - [Review Agent Work](https://docs.rudderhq.dev/how-to/review-agent-work): Open the real result, compare it with
NVIDIAllms.txtNVIDIA/TensorRT-Model-Connect/website/static/llms.txt
Preserve user changes and inspect branch, status, and remotes before editing. - Do not weaken tests or thresholds to make CI pass. - Use exact model revision, family manifest, task, precision, topology
vidispinellms.txtvidispine/hull/llms.txt
write-check-fix workflow, transformations, kind mapping and common mistakes - [Cookbook](https://raw.githubusercontent.com/vidispine/hull/main/hull/files/doc/cookbook.md): tested recipes for common tasks, from a web application to hooks, RBAC and storage - [Error codes
nyx-spacellms.txtnyx-space/anise/llms.txt
steps. 4. **Dependencies**: - The project depends on `cspice`. Ensure `CSPICE_DIR` is set for tests involving SPICE. - Rust feature flags like `python` and `analysis` may be needed for certain functionalities
ohad6kllms.txtohad6k/emulo/site/llms.txt
personal folder that is not committed. In a host-by-host test on 2026-09-25, a project AGENTS.md reached the model in Codex (verified
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.
