agentleFS
Sign inStart free
akashgitakashgit/remote-factory/AGENTS.md

remote-factory

AGENTS.md74 starsChanged 38 days agoMITView on GitHub

This file provides guidance to Codex CLI and other AGENTS.md-compatible tools when working with this repository. Tests use pytest-asyncio with asyncio_mode = "auto". The factory is a three-layer system: Agent roles: Researcher, Strategist, Builder, Reviewer, Evaluator, Archivist, Distiller, Failure Analyst, CEO. Key modules: factory/adversarial.py (GAN-style adversarial eval loops — phase transitions with hysteresis, convergence detection, state at .factory/adversarial_state.json). The factory exposes tools via MCP (Model Context Protocol): Or configure in ~/.codex/config.toml:

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 1

    1. boston-harness-group/remote-factory★ 74100% same

    Edited · 0

    None found.

    Wrote their own version · 0

    None found.

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository8 other files it gives its agents.

The file

Create a free account to mount
Files
AGENTS.md
<!-- Keep in sync with CLAUDE.md -->

AGENTS.md

This file provides guidance to Codex CLI and other AGENTS.md-compatible tools when working with this repository.

Build & Run

uv sync                          # Install all deps (including dev group)
factory --help                   # Verify CLI entry point

Test

pytest -v                        # Full suite
pytest tests/test_models.py -v   # Single file
pytest -k "test_detect" -v       # By name pattern
pytest --cov                     # With coverage

Tests use pytest-asyncio with asyncio_mode = "auto".

Lint & Type Check

ruff check .                     # Lint
ruff check --fix .               # Lint with autofix
mypy factory/                    # Type check

Style

  • Python 3.11+, use X | Y unions, not Union[X, Y]
  • Snake_case everywhere
  • 100 char line length (enforced by ruff)
  • Pydantic models use ConfigDict(strict=True, extra="forbid")
  • Async/await by default
  • Structured logging via structlog

Architecture

The factory is a three-layer system:

  1. Python CLI (factory/cli/): Pure tools that don't make decisions. Entry point is factory/cli/_main.py.
  2. CEO Agent (factory/agents/prompts/ceo.md): Orchestrates the full workflow. Spawned via factory ceo /path.
  3. Specialist Agents (factory/agents/): Eight subprocesses spawned by the CEO via factory agent <role>.

Agent roles: Researcher, Strategist, Builder, Reviewer, Evaluator, Archivist, Distiller, Failure Analyst, CEO.

Key modules: factory/adversarial.py (GAN-style adversarial eval loops — phase transitions with hysteresis, convergence detection, state at .factory/adversarial_state.json).

MCP Server

The factory exposes tools via MCP (Model Context Protocol):

factory serve-mcp

Or configure in ~/.codex/config.toml:

[mcp_servers.factory]
command = "factory"
args = ["serve-mcp"]

Installing Agents

factory install --runner codex    # Install TOML agents to ~/.codex/agents/
factory install --runner claude   # Install Markdown agents to ~/.claude/agents/

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