agentleFS
Sign inStart free
NandhaKishorMNandhaKishorM/laya/AGENTS.md

laya

AGENTS.md35k starsChanged 52 days agoApache-2.0View on GitHub

Context for AI coding assistants (Claude Code, Codex, Cursor, Copilot, Gemini CLI) working in this repository. Laya is a fast, local, on-device decision engine. These rules mirror CONTRIBUTING.md; the assistant-facing summary lives here because coding agents read this file automatically. Optional extras are declared in pyproject.toml (serve, fast, onnx, langchain, langgraph); install only what the change needs.

  • Installs packages

Trending

More talk lately.about the whole repository

Dec 2025: 0 mentionsJan 2026: 0 mentionsFeb 2026: 0 mentionsMar 2026: 0 mentionsApr 2026: 0 mentionsMay 2026: 0 mentionsJun 2026: 0 mentionsJul 2026: 0 mentionsAug 2026: 0 mentionsSep 2026: 44 mentionsOct 2026: 12 mentionsNov 2026: 46 mentions
Dec 2025Jun 2026Nov 2026
Mentions a month of the NandhaKishorM/laya repository that our weekly crawl found. There is no adoption data for this file yet.

Who's talking about NandhaKishorM/laya

The biggest 5 of 102 mentions linking to the repository that our crawl found. Each line is their own headline.

See all 102

Talked about on GitHub, YouTube, Bluesky, the web and Hacker News (102 times).

On GitHub · 50

45 more on GitHub

On YouTube · 24

19 more on YouTube

On Bluesky · 14

9 more on Bluesky

On the web · 13

8 more on the web
  • 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 31,542 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

4 rules. About 1 is common, 3 are distinctive, and 0 are very specific to this project.

  • ≈1

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Common:

    Commit secrets, tokens, or large binary files.

    line 19
  2. Distinctive:

    Keep it focused; split unrelated work into another PR.

    line 38
  3. Distinctive:

    If a change moves numbers, report the before and after.

    line 39
  4. Distinctive:

    Leave one runnable check behind for non-trivial logic.

    line 40

≈ “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

AGENTS.md

Context for AI coding assistants (Claude Code, Codex, Cursor, Copilot, Gemini CLI) working in this repository.

Laya is a fast, local, on-device decision engine. These rules mirror CONTRIBUTING.md; the assistant-facing summary lives here because coding agents read this file automatically.

Do NOT

  • Introduce a dependency on a hosted service or external API. Features must run in the user's own process or on their own hardware; a feature that only works against a hosted backend belongs in a separate integration, not here.
  • Change the public API without updating tests/test_hooks_api.py in the same pull request — that suite is the API contract.

  • Skip the CI gates before declaring a change done:

    ruff check laya/ --select=E9,F63,F7,F82,F401,F811 --line-length=120
python -m compileall -q laya/ tests/
  • Reformat files wholesale, reorder imports, or "modernize" surrounding code. Match the style of the file being edited; a diff full of formatting noise gets a change rejected.
  • Commit secrets, tokens, or large binary files.
  • Open pull requests in a language other than English. The project is triaged in English.
  • Invent conventions. Use conventional commit prefixes matching the history (feat(agent):, fix(router):, perf(common):, docs(hooks):, test(batch):), and keep one logical change per commit.

Where to look

EditingReadCheck
laya/ core—plain script suites: python tests/test_router.py, tests/test_criteria.py, tests/test_hooks.py, tests/test_hooks_api.py
server pathtests/test_serve.pypython -m pytest tests/test_serve.py (skips when the serve extra is missing)
ONNX pathtests/test_onnx.pypython -m pytest tests/test_onnx.py (skips when the onnx extra is missing)
fast/local pathstests/test_fast.py, tests/test_local_e2e.py, tests/test_mcp_local_e2e.pyneed CUDA or checkpoints under ~/laya_models; skipped otherwise
docs, docstrings in laya/docs/, docs/.nav.yml for page orderpip install -r requirements-docs.txt, then zensical build --strict --clean with no griffe: lines in the output

Optional extras are declared in pyproject.toml (serve, fast, onnx, langchain, langgraph); install only what the change needs.

Pull requests

  • Rebase onto the latest main so the diff is only your change.
  • Keep it focused; split unrelated work into another PR.
  • If a change moves numbers, report the before and after. The maintainer verifies decisions against real checkpoints, and measured deltas (probability changes, latency, memory) are what gets a change merged.
  • Leave one runnable check behind for non-trivial logic; an assert-based script is enough.

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