Important

The active Rust workspace now lives in rust/. Start with USAGE.md for build, auth, CLI, session, and parity-harness workflows, then use rust/README.md for crate-level details.

If you find this work useful, consider sponsoring @instructkr on GitHub to support continued open-source harness engineering research.

Backstory

At 4 AM on March 31, 2026, the Claude Code source was exposed, and the entire dev community was in a frenzy. What followed wasn't a typical human-led engineering effort—it was the first large-scale autonomous coding operation orchestrated entirely by AI agents.

This repository is maintained by lobsters and claws—autonomous AI coding agents created by Bellman (@bellman_ych) and Yeongyu (@q_yeon_gyu_kim). The entire Python port, from reading the original harness structure to producing a working tree with tests, was driven through oh-my-codex (OmX) using $team mode for parallel code review and $ralph mode for persistent execution loops with architect-level verification. No human wrote the core implementation—every line was generated, reviewed, and refined by autonomous agents.

The result is a clean-room Python rewrite that captures the architectural patterns of Claude Code's agent harness without copying any proprietary source. This isn't merely a port; it's a demonstration of what autonomous coding harnesses can achieve when directed by clear architectural vision and rigorous agent orchestration.

We are actively pushing this further. The basic Python foundation is already in place and functional, but we're just getting started. Stay tuned—a much more capable version is on the way.

https://github.com/ultraworkers/claw-code

The Creators

claw-code is autonomously built and maintained by UltraWorkers — a collective of AI coding agents (lobsters and claws) orchestrated by:

Bellman (@bellman_ych) — Creator of oh-my-codex (OmX), the agent orchestration layer that drives all development
Yeongyu (@q_yeon_gyu_kim) — Architect of the claw-code harness and parallel agent workflows

The entire codebase—from initial port to ongoing feature development—is generated through autonomous agent sessions using OmX $team and $ralph modes. No human writes the core implementation; humans provide architectural direction, agents execute.

Featured Coverage

Sigrid Jin has been deeply involved in harness engineering—studying how agent systems wire tools, orchestrate tasks, and manage runtime context. Coverage from The Wall Street Journal (March 21, 2026) documents the rise of autonomous coding:

AI startup worker Sigrid Jin, who attended the Seoul dinner, single-handedly used 25 billion of Claude Code tokens last year. At the time, usage limits were looser, allowing early enthusiasts to reach tens of billions of tokens at a very low cost.

"It was basically like a sharing party," Jin said. "There were lawyers, there were doctors, there were dentists. They did not have software engineering backgrounds."

— The Wall Street Journal, March 21, 2026, "The Trillion Dollar Race to Automate Our Entire Lives"

Porting Status

The main source tree is now Python-first.

src/ contains the active Python porting workspace
tests/ verifies the current Python workspace
the exposed snapshot is no longer part of the tracked repository state

The current Python workspace is not yet a complete one-to-one replacement for the original system, but the primary implementation surface is now Python.

Why this rewrite exists

I originally studied the exposed codebase to understand its harness, tool wiring, and agent workflow. After spending more time with the legal and ethical questions—and after reading the essay linked below—I did not want the exposed snapshot itself to remain the main tracked source tree.

This repository now focuses on Python porting work instead.

Repository Layout

.
├── src/                                # Python porting workspace
│   ├── __init__.py
│   ├── commands.py
│   ├── main.py
│   ├── models.py
│   ├── port_manifest.py
│   ├── query_engine.py
│   ├── task.py
│   └── tools.py
├── tests/                              # Python verification
├── assets/omx/                         # OmX workflow screenshots
├── 2026-03-09-is-legal-the-same-as-legitimate-ai-reimplementation-and-the-erosion-of-copyleft.md
└── README.md

Python Workspace Overview

The new Python src/ tree currently provides:

port_manifest.py — summarizes the current Python workspace structure
models.py — dataclasses for subsystems, modules, and backlog state
commands.py — Python-side command port metadata
tools.py — Python-side tool port metadata
query_engine.py — renders a Python porting summary from the active workspace
main.py — a CLI entrypoint for manifest and summary output

Quickstart

Render the Python porting summary:

python3 -m src.main summary

Print the current Python workspace manifest:

python3 -m src.main manifest

List the current Python modules:

python3 -m src.main subsystems --limit 16

Run verification:

python3 -m unittest discover -s tests -v

Run the parity audit against the local ignored archive (when present):

python3 -m src.main parity-audit

Inspect mirrored command/tool inventories:

python3 -m src.main commands --limit 10
python3 -m src.main tools --limit 10

Current Parity Checkpoint

The port now mirrors the archived root-entry file surface, top-level subsystem names, and command/tool inventories much more closely than before. However, it is not yet a full runtime-equivalent replacement for the original TypeScript system; the Python tree still contains fewer executable runtime slices than the archived source.

Built with `oh-my-codex`

The restructuring and documentation work on this repository was AI-assisted and orchestrated with Yeachan Heo's oh-my-codex (OmX), layered on top of Codex.

$team mode: used for coordinated parallel review and architectural feedback
$ralph mode: used for persistent execution, verification, and completion discipline
Codex-driven workflow: used to turn the main src/ tree into a Python-first porting workspace

OmX workflow screenshots

Ralph/team orchestration view while the README and essay context were being reviewed in terminal panes.

Split-pane review and verification flow during the final README wording pass.

Community

Join the UltraWorkers Discord — the community around clawhip, oh-my-openagent, oh-my-claudecode, oh-my-codex, and claw-code. Come chat about LLMs, harness engineering, agent workflows, and autonomous software development.

Star History

See the chart at the top of this README.

Ownership / Affiliation Disclaimer

This repository does not claim ownership of the original Claude Code source material.
This repository is not affiliated with, endorsed by, or maintained by Anthropic.

README.md

Rewriting Project Claw Code