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.
Cloudflarellms.txtcloudflare/chanfana/llms.txt
help AI tools understand the library: - `AGENTS.md` — Comprehensive development guide: architecture, patterns, migration notes, testing - `skills/write-endpoints/SKILL.md` — Step-by-step coding skill for building endpoints with chanfana - `docs/` — Full user documentation
erickochenPipes a download into a shellllms.txterickochen/purple/llms.txt
# purple > Keeps ~/.ssh/config in sync with your cloud infra. Spin up a VM on
HelpCode-aiReads credentialsllms.txtHelpCode-ai/anythingmcp/llms-full.txt
# AnythingMCP > Turn any REST/OpenAPI, SOAP/WSDL, GraphQL, OData or SQL API into MCP tools for
HelpCode-aillms.txtHelpCode-ai/anythingmcp/llms.txt
server of the workspace... ## Contributing - [Contributing to AnythingMCP](https://raw.githubusercontent.com/HelpCode-ai/anythingmcp/main/.github/CONTRIBUTING.md): Set up development, test changes, and submit a contribution. - [Agent instructions](https://raw.githubusercontent.com/HelpCode-ai/anythingmcp/main/AGENTS.md): Repository instructions, setup commands, tests
AbilityaiPipes a download into a shellllms.txtAbilityai/trinity/llms.txt
architecture explained, workshops and demos - [Security policy](SECURITY.md) and [UnderDefense attestation](docs/security/UnderDefense-Web-Pentest-Attestation-Apr-2026.pdf) - [Contributing](CONTRIBUTING.md), [Testing strategy](docs/testing/STRATEGY.md), [Known issues](docs/KNOWN_ISSUES.md) - [Website](https://www.ability.ai/trinity): product page · [Workshops](https://www.ability.ai/workshops):
mental-osllms.txtmental-os/Aurora-OS.js/public/llms-full.txt
wipes everything. - **Helper Functions**: `getAppStateKey(appId, user)` and `getWindowKey(user)` generate correctly-prefixed keys. - **Tests**: Test assertions MUST use `STORAGE_KEYS.*` constants, never hardcoded key strings. - **FS Integrity**: ALWAYS
alekspetrovllms.txtalekspetrov/pilot/llms.txt
tickets into pull requests. Label a GitHub issue with "pilot" and Pilot handles implementation, testing, and PR creation. ## Quick Integration **Trigger Pilot**: Create a GitHub issue with the `pilot` label
logicrwReads credentialsllms.txtlogicrw/awesome-jev-projects/public/llms-full.txt
separate Jev scripts were inspected; desktop behavior and end-to-end latency were not tested here. - License: Apache-2.0 - Details: https://logicrw.github.io/awesome-jev-projects/en/projects/jev-desktop/ - Source evidence: https://github.com/lahfir/agent-desktop/blob/7a8e4a10281c7319733aa200fd79501f34529716/README.md - Source evidence
g-battagliallms.txtg-battaglia/kerykeion/kerykeion/llms.txt
inside the band, speed rising — the phase closes). The band brackets zero and is tested before the sign, so a body creeping backwards inside it reports a station, not `retrograde
Tencentllms.txtTencent/BqLog/llms.txt
throughput, peak memory and output file size vs spdlog, quill, fmtlog, glog, Log4j2, with test code - [Integration Guide](https://github.com/Tencent/BqLog/blob/main/docs/INTEGRATION_GUIDE.md): how to integrate in standard environments - [Configuration](https://github.com
Xilinxllms.txtXilinx/mlir-aie/docs/llms.txt
Also supports AMD Versal™ AI Engine devices, though the NPU path is the actively-tested focus
kossisoroycellms.txtkossisoroyce/timber/llms.txt
class probabilities. Q: What Python versions are supported? A: Python 3.10, 3.11, and 3.12. Tested on Ubuntu and macOS. Q: What C compiler is required? A: gcc (preferred) or clang
pompelmillms.txtpompelmi/pompelmi/llms.txt
scanUpload`, `scanFormData` for +page.server.ts and +server.ts) - `@pompelmi/nextjs` — Next.js App Router / Pages Router helpers - `@pompelmi/testing` — test utilities (`mockClean`, `mockInfected`, `withMockedPompelmi`) ## Installation npm install pompelmi ClamAV must be installed separately: `brew install
genomoncologyllms.txtgenomoncology/biomcp/docs/llms-full.txt
biomcp.org/sources/gnomad/): Access details and query guidance for the gnomAD data source. - [NCBI Genetic Testing Registry](https://biomcp.org/sources/gtr/): Access details and query guidance for the NCBI Genetic Testing Registry
nubenetesllms.txtnubenetes/awesome-kubernetes/v2-docs/llms.txt
Chaos Engineering](https://nubenetes.com/chaos-engineering/) - [Developerportals](https://nubenetes.com/developerportals/) - [DevOps](https://nubenetes.com/devops/) - [Performance Testing With Jenkins And Jmeter](https://nubenetes.com/performance-testing-with-jenkins-and-jmeter/) - [Project Management Methodology](https://nubenetes.com/project-management-methodology/) - [Project Management
decionisllms.txtdecionis/agent-safe-pipeline/llms-full.txt
github.com/decionis/agent-safe-pipeline/blob/master/spec/intent/v1/README.md, https://github.com/decionis/agent-safe-pipeline/blob/master/spec/intent/v1/schema.json, https://github.com/decionis/agent-safe-pipeline/blob/master/spec/intent/v1/CHANGELOG.md, https://github.com/decionis/agent-safe-pipeline/blob/master/spec/intent/v1/frameworks.md - The Compromised Principal Test (valid identity + valid access ≠ authorized execution: the test, three ways to run it in under
decionisllms.txtdecionis/agent-safe-pipeline/llms.txt
github.com/decionis/agent-safe-pipeline/blob/master/spec/intent/v1/README.md, https://github.com/decionis/agent-safe-pipeline/blob/master/spec/intent/v1/schema.json, https://github.com/decionis/agent-safe-pipeline/blob/master/spec/intent/v1/CHANGELOG.md, https://github.com/decionis/agent-safe-pipeline/blob/master/spec/intent/v1/frameworks.md - The Compromised Principal Test (valid identity + valid access ≠ authorized execution: the test, three ways to run it in under
ojuschugh1llms.txtojuschugh1/sqz/llms.txt
client config - [Quality benchmark](https://github.com/ojuschugh1/sqz/blob/main/docs/quality-benchmark.md): compression ratio vs information preservation, regression-tested - [Context rot vs context compression](https://github.com/ojuschugh1/sqz/blob/main/docs/context-rot.md): proactive vs reactive context management - [Choosing a context
carloslfuPipes a download into a shellllms.txtcarloslfu/slotstream/llms-full.txt
measured **20.91–23.69 tok/s** across three workloads in development tests at a 33 GB memory budget, using the original 4-bit model ([results and test conditions](#speed)). [Get started](#install
carloslfuPipes a download into a shellllms.txtcarloslfu/slotstream/llms.txt
Apple Silicon Macs with far less RAM than the > model: October 5, 2026 development tests measured 20.91–23.69 tok/s across three > workloads
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.
