agentleFS
Sign inStart free
vllm-projectvllm-project/aibrix/AGENTS.md

aibrix

AGENTS.md5.2k starsChanged 57 days agoApache-2.0View on GitHub

AIBrix is a Kubernetes-native platform for scalable GenAI inference infrastructure. - Understand the problem and define success before making a non-trivial change. Ground decisions in existing implementations, tests, and verified evidence; do not infer behavior from filenames. - Make the smallest coherent change. Preserve unrelated work and existing conventions; avoid speculative abstractions and unrelated cleanup. - Treat public contracts and compatibility as design constraints. Keep API definitions declarative and policy in the layer that owns it. Preserve API, HTTP, CLI,…

Trending

More talk lately.about the whole repository

Dec 2025: 2 mentionsJan 2026: 1 mentionFeb 2026: 2 mentionsMar 2026: 0 mentionsApr 2026: 1 mentionMay 2026: 2 mentionsJun 2026: 4 mentionsJul 2026: 0 mentionsAug 2026: 0 mentionsSep 2026: 3 mentionsOct 2026: 5 mentionsNov 2026: 0 mentions
Dec 2025Jun 2026Nov 2026
Mentions a month of the vllm-project/aibrix repository that our weekly crawl found. There is no adoption data for this file yet.

Who's talking about vllm-project/aibrix

The biggest 5 of 39 mentions linking to the repository that our crawl found. Each line is their own headline.

See all 39

Talked about on GitHub, Bluesky and Hacker News (39 times).

On GitHub · 34

29 more on GitHub
  • Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.

    Of the AGENTS.md files we read, the 31,774 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.

The file

We split this AGENTS.md into the rules it gives an agent

6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Treat public contracts and compatibility as design constraints.

    line 12
  2. Distinctive:

    Verify observable behavior at the narrowest useful level, then expand checks to match the change's scope.

    line 15
  3. Distinctive:

    Keep documentation and generated artifacts consistent with the implementation.

    line 18
  4. Very specific:

    Before implementing a feature or bug fix for a non-maintainer, check existing issues and PRs and wait for a maintainer to apply …

    line 26
  5. Distinctive:

    Read the relevant guide before changing that area.

    line 42
  6. Distinctive:

    Before implementation or PRs: Contribution policy.

    line 45

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
AGENTS.md

AIBrix

AIBrix is a Kubernetes-native platform for scalable GenAI inference infrastructure.

Principles

  • Understand the problem and define success before making a non-trivial change. Ground decisions in existing implementations, tests, and verified evidence; do not infer behavior from filenames.
  • Make the smallest coherent change. Preserve unrelated work and existing conventions; avoid speculative abstractions and unrelated cleanup.
  • Treat public contracts and compatibility as design constraints. Keep API definitions declarative and policy in the layer that owns it. Preserve API, HTTP, CLI, configuration, and metadata contracts; plan compatibility migrations.
  • Verify observable behavior at the narrowest useful level, then expand checks to match the change's scope. Report what ran, what passed, and what remains unverified.
  • Keep documentation and generated artifacts consistent with the implementation. Review every generated or AI-assisted change; submit only what you can explain.
  • Respect authorization boundaries. Do not push, rewrite history, change remote GitHub state, or send external messages without explicit authorization. Ask before upgrading dependencies or changing workflow policy under .github/.

Contribution gates

  • Before implementing a feature or bug fix for a non-maintainer, check existing issues and PRs and wait for a maintainer to apply triage/accepted to the issue. Until then, limit work to investigation, reproduction, and improving the issue; do not implement the change or prepare a PR.
  • Maintainers listed on the community page may self-triage routine fixes. Sensitive or broad changes still require prior discussion and independent maintainer review.
  • Pure documentation corrections and obvious mechanical fixes may proceed without an accepted issue only if they do not change behavior, configuration, dependencies, workflows, APIs, or generated files. Test-only changes are not automatically exempt; identify the real behavior or risk they protect.
  • Acceptance covers the problem and direction, not approval of a patch. Return to the issue for agreement before materially expanding the accepted scope.

Task guides

Read the relevant guide before changing that area; use the sections needed for this task. Rules in a deeper AGENTS.md take precedence for that directory.

  • Before implementation or PRs: Contribution policy.
  • Go, APIs, controllers, and code generation: Development guide.
  • Tests: Test guide.
  • Documentation and translations: Documentation guide.
  • Python runtime: python/aibrix/AGENTS.md.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

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.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free