agentleFS
Sign inStart free
guoliang1114-boopguoliang1114-boop/AriaAI/AGENTS.md

AriaAI

AGENTS.md40 starsChanged 3 months agoMITView on GitHub

This file is the Codex entry point for the repository. Read agent.md before changing code; it is the complete project guide and remains the source of truth for repository layout, architecture, deployment, and collaboration rules. - Preserve user changes and unrelated work. Never discard a dirty worktree. - Keep product/domain state and execution control in AriaAI. Projects, clients, memory, tasks, artifacts, approvals, permissions, and audit history always belong to Aria's native services. - Treat backend/app/services/chat/product_run_events.py as the backend run event…

The file

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

6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Keep product/domain state and execution control in AriaAI.

    line 10
  2. Very specific:

    Treat backend/app/services/chat/product_run_events.py as the backend run event contract and web/src/types/productRunEvent.ts as its …

    line 13
  3. Distinctive:

    Do not add a Codex App Server, Codex SDK, Codex subprocess, or Codex protocol dependency to the Aria application runtime.

    line 17
  4. Distinctive:

    When adapting useful open-source implementations, port the smallest cohesive mechanism into Aria's language and architecture.

    line 20
  5. Distinctive:

    Add focused tests with every behavioral change.

    line 30
  6. Distinctive:

    Update the relevant design or operations document when changing a public event, runtime boundary, approval flow, data model, or deployment …

    line 34

≈ “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

AriaAI Agent Guide

This file is the Codex entry point for the repository. Read agent.md before changing code; it is the complete project guide and remains the source of truth for repository layout, architecture, deployment, and collaboration rules.

Working contract

  • Preserve user changes and unrelated work. Never discard a dirty worktree.
  • Keep product/domain state and execution control in AriaAI. Projects, clients, memory, tasks, artifacts, approvals, permissions, and audit history always belong to Aria's native services.
  • Treat backend/app/services/chat/product_run_events.py as the backend run event contract and web/src/types/productRunEvent.ts as its frontend mirror.
  • Route consequential writes through AriaAI authorization and HITAS. A model, provider, or filesystem-sandbox decision is not business authorization.
  • Do not add a Codex App Server, Codex SDK, Codex subprocess, or Codex protocol dependency to the Aria application runtime. Codex may be used as a developer tool, but Aria does not communicate with Codex in production.
  • When adapting useful open-source implementations, port the smallest cohesive mechanism into Aria's language and architecture. Record its upstream commit, source path, license, attribution, and Aria modifications. Keep the current model-provider paths intact and verify behavior with focused tests.

Development loop

  • Backend commands run from backend/ with backend/.venv/bin/python when the checked-in virtual environment exists.
  • Frontend commands run from web/.
  • Add focused tests with every behavioral change. Run focused tests first, then the broader affected suite.
  • Database changes require an idempotent Alembic revision with exactly one migration head. Do not rely only on SQLModel.metadata.create_all.
  • Update the relevant design or operations document when changing a public event, runtime boundary, approval flow, data model, or deployment contract.

Useful checks

cd backend
.venv/bin/python -m pytest -q tests/test_agent_harness_native.py
.venv/bin/python -m pytest -q tests/test_product_run_events.py

cd ../web
npm test -- --run src/stores/runActivityReducer.test.ts
npm run build

Repository skills

Curated developer-agent discovery links live in .agents/skills/. They are development metadata only and are never loaded by the Aria production runtime. Canonical Aria Skill packages remain under skills/.

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