agentleFS
Sign inStart free
vpeetla-aivpeetla-ai/multi-agent-system-pattern/AGENTS.md

multi-agent-system-pattern

AGENTS.md2 starsChanged 5 months agoMITView on GitHub

Read CONTEXT.md for shared vocabulary. This org builds governed agent systems, not chat demos: Install org skills from vpeetla-ai-skills:

  • Installs packages

5 other projects use a version of this.

Adopted by

Most recently taken up by

The file

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

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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:

    Read CONTEXT.md for shared vocabulary.

    line 3
  2. Distinctive:

    Check which stack layer the task belongs to

    line 39
  3. Very specific:

    Read the target repo's docs/ECOSYSTEM.md or docs/ARCHITECTURE.md

    line 40
  4. Distinctive:

    Use tdd-agent-loops for graph changes.

    line 41

≈ “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

Agent Instructions — vpeetla-ai org

Read CONTEXT.md for shared vocabulary.

Agentic engineering (Karpathy)

  1. Think before coding — state assumptions, plan, success criteria
  2. Simplicity first — minimum diff; no speculative features
  3. Surgical changes — match existing style; no drive-by refactors
  4. Goal-driven execution — tests/evals define done; iterate until pass

Stack awareness

This org builds governed agent systems, not chat demos:

  • Orchestration (VAP) and governance (AegisAI) are separate layers
  • RAG uses access-before-ranking
  • Side effects require gateway or HITL
  • Self-improvement uses harness + eval loops (LoopForge)

Repo conventions

  • Python 3.11+, FastAPI, Pydantic v2, LangGraph for agent graphs
  • pip install -e ".[dev]" + pytest -q before claiming done
  • README: badges → problem → 60s diagram → honest status table → quick start
  • Deploy: Vercel (UI) + Render (API); see render.yaml

Skills repo

Install org skills from vpeetla-ai-skills:

./scripts/install.sh --cursor --project .
./scripts/install.sh --codex --project .

When stuck

  1. Check which stack layer the task belongs to
  2. Read the target repo's docs/ECOSYSTEM.md or docs/ARCHITECTURE.md
  3. Use tdd-agent-loops for graph changes; aegis-gateway for side effects

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