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.
ppgrangerllms.txtppgranger/token-saver/docs/llms.txt
tool family) - [git](https://ppgranger.github.io/token-saver/processors/git/): status, diff, log, show, push/pull/fetch, branch, stash, blame. - [test_output](https://ppgranger.github.io/token-saver/processors/test_output/): pytest, jest, go test, cargo test and other test runners. - [lint
ZIZKA-AI-SLPipes a download into a shellllms.txtZIZKA-AI-SL/ZizkaDB/llms.txt
coding agents - [CLAUDE.md](https://github.com/ZIZKA-AI-SL/ZizkaDB/blob/main/CLAUDE.md) and [AGENTS.md](https://github.com/ZIZKA-AI-SL/ZizkaDB/blob/main/AGENTS.md): stack, conventions, invariants, test commands - [CONTRIBUTING.md](https://github.com/ZIZKA-AI-SL/ZizkaDB/blob/main/CONTRIBUTING.md)
Lolner95llms.txtLolner95/AIGX/llms.txt
context > format known to be validated by a controlled benchmark: #1 of all formats tested on mean score, pass@1, > and hidden-test pass rate on both Claude Haiku
nexscope-aillms.txtnexscope-ai/ecommerce-ai-tools/docs/llms.txt
agents - https://learn.nexscope.ai/ecommerce-ai-tools/topics/creative/ — product image and video workflows - https://learn.nexscope.ai/ecommerce-ai-tools/topics/evidence/ — test records and case studies ## Core guides - https://learn.nexscope.ai/ecommerce-ai-tools/ecommerce-mcp-server/ — connect marketplace research APIs to AI agents with
lbednerReads credentialsllms.txtlbedner/aegis-stack/llms.txt
backend, frontend, scheduler) │ ├── services/ # Business logic (explicit imports) │ ├── core/ # Framework utilities │ └── integrations/ # App composition ├── tests/ # Test suite ├── pyproject.toml # Dependencies based on selected components ├── Dockerfile # Container definition └── docker-compose.yml # Multi-service orchestration
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
rubenmarcusllms.txtrubenmarcus/aeo.js/llms.txt
Human/AI view-toggle widget - `website/` — Astro Starlight docs (aeojs.org) - `demo/` — per-framework example apps - `tests` — colocated `*.test.ts`, vitest, 327 tests ## Commands ```bash npm install npm test # vitest npx tsc --noEmit
nirholasllms.txtnirholas/pump-fun-sdk/llms-full.txt
encryption support - batch-generate.sh — Parallel batch with resume - verify-keypair.sh — 7-point verification - test-rust.sh — Rust test runner - utils.sh — Shared utilities - publish-clawhub.sh — Publishing script - scrape-site.mjs — Site scraping - screenshot-site.mjs — Site screenshots ### Verification Tools (tools
nirholasllms.txtnirholas/pump-fun-sdk/llms.txt
scripts/ - Production Bash wrappers (vanity generation, verification, site tools) - tools/ - Audit and verification utilities - tests/ - Integration, fuzz, stress, benchmark, and CLI tests - docs/ - Full documentation including official Pump protocol specs
adham90llms.txtadham90/ruby_llm-agents/LLMS.txt
Sending files and images to agents ## Evaluation - [Evaluation Guide](wiki/Evaluation.md): Score agent quality with test datasets and built-in scorers - [EvalSuite](lib/ruby_llm/agents/eval/eval_suite.rb): DSL for defining test cases, running them
hidai25Reads credentialsllms.txthidai25/eval-view/llms-full.txt
EvalView — Complete Documentation for AI Systems > Regression testing for AI agents. Snapshot behavior, detect regressions, block broken agents before production. ## Identity - Name: EvalView - Tagline: "Proof that your agent still works
hidai25llms.txthidai25/eval-view/llms.txt
EvalView > Regression testing for AI agents. Snapshot behavior, detect regressions, block broken agents before production. EvalView is an open-source testing and regression detection framework for AI agents. It sends
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
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.
