⭐ The fastest repo in history to surpass 50K stars, reaching the milestone in just 2 hours after publication ⭐
Better Harness Tools, not merely storing the archive of leaked Claude Code
> [!IMPORTANT]
> **Rust port is now in progress** on the [`dev/rust`](https://github.com/instructkr/claw-code/tree/dev/rust) branch and is expected to be merged into main today. The Rust implementation aims to deliver a faster, memory-safe harness runtime. Stay tuned — this will be the definitive version of the project.
> If you find this work useful, consider [sponsoring @instructkr on GitHub](https://github.com/sponsors/instructkr) to support continued open-source harness engineering research.
---
## Backstory
At 4 AM on March 31, 2026, I woke up to my phone blowing up with notifications. The Claude Code source had been exposed, and the entire dev community was in a frenzy. My girlfriend in Korea was genuinely worried I might face legal action from Anthropic just for having the code on my machine — so I did what any engineer would do under pressure: I sat down, ported the core features to Python from scratch, and pushed it before the sun came up.
The whole thing was orchestrated end-to-end using [oh-my-codex (OmX)](https://github.com/Yeachan-Heo/oh-my-codex) by [@bellman_ych](https://x.com/bellman_ych) — a workflow layer built on top of OpenAI's Codex ([@OpenAIDevs](https://x.com/OpenAIDevs)). I used `$team` mode for parallel code review and `$ralph` mode for persistent execution loops with architect-level verification. The entire porting session — from reading the original harness structure to producing a working Python tree with tests — was driven through OmX orchestration.
The result is a clean-room Python rewrite that captures the architectural patterns of Claude Code's agent harness without copying any proprietary source. I'm now actively collaborating with [@bellman_ych](https://x.com/bellman_ych) — the creator of OmX himself — to push 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/instructkr/claw-code
## The Creators Featured in Wall Street Journal For Avid Claude Code Fans
I've been deeply interested in **harness engineering** — studying how agent systems wire tools, orchestrate tasks, and manage runtime context. This isn't a sudden thing. The Wall Street Journal featured my work earlier this month, documenting how I've been one of the most active power users exploring these systems:
> 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.
>
> Despite his countless hours with Claude Code, Jin isn't faithful to any one AI lab. The tools available have different strengths and weaknesses, he said. Codex is better at reasoning, while Claude Code generates cleaner, more shareable code.
>
> Jin flew to San Francisco in February for Claude Code's first birthday party, where attendees waited in line to compare notes with Cherny. The crowd included a practicing cardiologist from Belgium who had built an app to help patients navigate care, and a California lawyer who made a tool for automating building permit approvals using Claude Code.
>
> "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"*](https://lnkd.in/gs9td3qd)
---
## 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
```text
.
├── 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:
```bash
python3 -m src.main summary
```
Print the current Python workspace manifest:
```bash
python3 -m src.main manifest
```
List the current Python modules:
```bash
python3 -m src.main subsystems --limit 16
```
Run verification:
```bash
python3 -m unittest discover -s tests -v
```
Run the parity audit against the local ignored archive (when present):
```bash
python3 -m src.main parity-audit
```
Inspect mirrored command/tool inventories:
```bash
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)](https://github.com/Yeachan-Heo/oh-my-codex), 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 [**instructkr Discord**](https://instruct.kr/) — the best Korean language model community. Come chat about LLMs, harness engineering, agent workflows, and everything in between.
[](https://instruct.kr/)
## 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**.
=======
## 🧱 Rewriting Project Claw Code
Better harness tools, focused on execution not merely storing the archive of leaked Claude Code
---
## ⭐ Support
If you find this project useful, consider giving it a star ⭐
---
Claw Codes is actively being rewritten into a high-performance agent framework
Building better harness tools — focused on execution, not just structure or storage.
> [!IMPORTANT]
> A Rust-based core is currently in development and will serve as the foundation of the next phase of Claw Codes.
>
> This core is designed to:
> - improve execution speed
> - ensure memory safety
> - enable low-level system control
> - support scalable agent workflows
>
> Alongside this, a Python layer is being developed to handle orchestration, rapid iteration, and higher-level abstractions.
>
> The system is actively evolving and will undergo continuous architectural improvements.
---
## 🔄 Current Direction
Claw Codes is not a finished product.
It is a **system under active development**, with a focus on:
- 🦀 Rust-based core engine (in progress)
- 🐍 Python orchestration layer
- ⚙️ Improved execution pipeline
- 🧩 Modular system architecture
- 🔍 Continuous reverse engineering and refinement
- 🧠 Exploration of agent-based system design
Each part of the system is being designed with performance, clarity, and scalability in mind.
---
## 🧠 Vision
The goal of Claw Codes is to evolve into a foundation for:
- intelligent execution systems
- autonomous workflows
- agent-driven applications
- modular AI tooling infrastructure
Rather than focusing solely on generation, the system prioritizes:
> **Execution, control, and structured automation**
---
## 🛠 Features (In Development)
- Multi-agent task execution
- Tool-based architecture
- CLI-first interface
- Modular and extensible system design
- Local and remote execution support
- Structured workflow orchestration
- Plugin-ready architecture
---
## 🧩 Architecture Direction
Claw Codes is being designed with:
- Clear separation between components
- Defined boundaries between tools and agents
- Extensibility at every layer
- High-performance core (Rust)
- Flexible orchestration layer (Python)
---
## 🦀 Roadmap
- [ ] Core architecture stabilization
- [ ] Rust execution engine
- [ ] Python orchestration layer
- [ ] Tool system expansion
- [ ] Multi-agent coordination layer
- [ ] Plugin ecosystem
- [ ] Performance optimization
- [ ] CLI improvements
- [ ] Documentation expansion
---
## 🔍 Development Context
This project involves deep exploration into:
- agent execution systems
- orchestration patterns
- CLI-based AI workflows
- tool integration design
- system-level architecture
The implementation is being rebuilt independently with a focus on clean design and long-term scalability.
---
## Star History
This repository started gaining traction shortly after I backed up the code within a few hours of discovery.
---
## 🤝 Contributing
Contributions are welcome.
Ways to contribute:
- Improve system architecture
- Add new features
- Optimize performance
- Fix issues
- Suggest improvements
- Share ideas and feedback
---
## 📦 Status
Claw Codes is currently:
- under active development
- not yet stable
- continuously evolving
Expect frequent updates, restructuring, and improvements as the system matures.
---
## ⚠️ Disclaimer
Claw Codes is an independent, clean-room implementation and is **not affiliated with, endorsed by, or maintained by any organization or company referenced in this project**.
This repository is intended strictly for:
- Educational purposes
- Software architecture exploration
- Defensive and research-driven development
- Experimental AI system design
No proprietary claims are made over any external systems or codebases.
---
## 👤 Maintained By
**0xKarl:** https://x.com/0xKarl
---
## 💬 Support / Questions
For questions, discussions, or collaboration:
👉 Telegram: https://t.me/Carl_Crypt
Feel free to reach out if you’re interested in:
- the architecture
- contributions
- ideas and improvements
- general discussions about AI systems
---
>>>>>>> feat: init
