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/osv-scanner/llms.txt
extractor in `osv-scalibr/plugin/list/list.go` so it can be enabled by name. * Add thorough tests within `osv-scalibr`. * Get the changes merged into `osv-scalibr`. 2. **Enable in `osv-scanner
Steady4 mentions in 2 weeks
No other project uses it yet
gui-csllms.txtgui-cs/Terminal.Gui/llms.txt
recipes ### Contributing to Library (Contributor) - **Rules**: `AGENTS.md` and `.claude/rules/` - Coding conventions - **Workflows**: `.claude/workflows/` - Build, test, PR processes --- ## Core Concepts ### Correct Minimal App (v2) ```csharp using Terminal.Gui.App; using Terminal.Gui.Views; IApplication
No other project uses it yet
AWSllms.txtaws/amazon-sagemaker-examples/llms.txt
process and local-container modes, inference pipelines, multi-model and multi-container endpoints, A/B testing, shadow variants, deployment guardrails, autoscaling with inference components, `optimize()`, batch transform, Bedrock deployment, Marketplace model
No other project uses it yet
InsertKoinIOllms.txtInsertKoinIO/koin/llms.txt
whole graph at build time, DSL and Annotations alike. It replaces `checkModules()` / `verify()` tests. - **Koin KSP is deprecated** — never add `koin-ksp-compiler`, never import `org.koin.ksp.generated.*`, never pin `koin-annotations
Steady3 mentions in 2 weeks
No other project uses it yet
InsertKoinIOllms.txtInsertKoinIO/koin/projects/llms.txt
Coroutines (lazy modules) implementation("io.insert-koin:koin-ktor") // Ktor server implementation("io.insert-koin:koin-test") // Testing implementation("io.insert-koin:koin-test-junit5") // JUnit 5 testing // Never Koin KSP: no com.google.devtools.ksp
Steady3 mentions in 2 weeks
No other project uses it yet
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.
