⭐ 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 Claw Code
Important
Rust port is now in progress on the 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 to support continued open-source harness engineering research.
The entire Rust implementation under rust/ was ported and engineered using oh-my-opencode by @q_yeon_gyu_kim (@code-yeongyu) — an agent orchestration layer for opencode.
The Rust port is a complete, working CLI (claw) with:
- Streaming API client with SSE support
- Interactive REPL with markdown rendering
- Tool execution (bash, file read/write/edit, search)
- MCP (Model Context Protocol) stdio integration
- Plugin system with hooks pipeline
- CLAW.md project memory and config hierarchy
- OAuth authentication flow
- Session persistence and compaction
- HTTP/SSE server (axum-based, direct connect sessions)
- LSP client integration (diagnostics, go-to-definition, find-references)
- Vim keybinding mode (normal/insert/visual/command)
- Git slash commands (/branch, /commit, /commit-push-pr, /worktree)
Every crate, every test, every commit was driven through oh-my-opencode's Sisyphus agent with ultrawork mode — from initial scaffolding to the final cleanroom pass. The cleanroom refactor, QA verification, git history rewrite, and CI setup were coordinated by Jobdori (OpenClaw), an AI assistant orchestrating the entire workflow. The Rust port passes all 274 tests across the workspace.
cd rust && cargo build --release
./target/release/claw --help
Sisyphus is the agent that codes like your team. The Rust port was built entirely by Sisyphus in
ultraworkmode. Join the waitlist
"If Claude Code does in 7 days what a human does in 3 months, Sisyphus does it in 1 hour. It just works until the task is done." — B, Quant Researcher
"Hire @yeon_gyu_kim if you can convince him, this dude has revolutionized opencode." — mysticaltech
At 4 AM on March 31, 2026, I woke up to my phone blowing up with notifications. The Claw 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 the original authors 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) by @bellman_ych — a workflow layer built on top of OpenAI's Codex (@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 Claw Code's agent harness without copying any proprietary source. I'm now actively collaborating with @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.
The Rust port was built separately using oh-my-opencode (OMO) by @q_yeon_gyu_kim (@code-yeongyu), which orchestrates opencode agents. The Sisyphus agent handled everything — API client, runtime engine, CLI, plugin system, MCP integration, and the full cleanroom pass — all in ultrawork mode.
https://github.com/instructkr/claw-code
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 Claw 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 Claw 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 Claw Code generates cleaner, more shareable code.
Jin flew to San Francisco in February for Claw 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 Claw 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"
The main source tree is now Python-first.
src/contains the active Python porting workspacetests/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.
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.
.
├── src/ # Python porting workspace
│ ├── __init__.py
│ ├── commands.py
│ ├── main.py
│ ├── models.py
│ ├── port_manifest.py
│ ├── query_engine.py
│ ├── task.py
│ └── tools.py
├── rust/ # Rust port (claw CLI)
│ ├── crates/api/ # API client + streaming
│ ├── crates/runtime/ # Session, tools, MCP, config
│ ├── crates/claw-cli/ # Interactive CLI binary
│ ├── crates/plugins/ # Plugin system
│ ├── crates/commands/ # Slash commands
│ ├── crates/server/ # HTTP/SSE server (axum)
│ ├── crates/lsp/ # LSP client integration
│ └── crates/tools/ # Tool specs
├── 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
The new Python src/ tree currently provides:
port_manifest.py— summarizes the current Python workspace structuremodels.py— dataclasses for subsystems, modules, and backlog statecommands.py— Python-side command port metadatatools.py— Python-side tool port metadataquery_engine.py— renders a Python porting summary from the active workspacemain.py— a CLI entrypoint for manifest and summary output
Render the Python porting summary:
python3 -m src.main summaryPrint the current Python workspace manifest:
python3 -m src.main manifestList the current Python modules:
python3 -m src.main subsystems --limit 16Run verification:
python3 -m unittest discover -s tests -vRun the parity audit against the local ignored archive (when present):
python3 -m src.main parity-auditInspect mirrored command/tool inventories:
python3 -m src.main commands --limit 10
python3 -m src.main tools --limit 10The 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.
This repository's porting, cleanroom hardening, and verification workflow was AI-assisted with Yeachan Heo's tooling stack:
- oh-my-codex (OmX) — primary scaffolding, orchestration, and core porting workflow
- oh-my-opencode (OmO) — implementation acceleration, cleanup passes, and verification support
Key workflow patterns used during the port:
$teammode: coordinated parallel review and architectural feedback$ralphmode: persistent execution, verification, and completion discipline- Cleanroom passes: naming/branding cleanup, QA, and release validation across the Rust workspace
- Manual and live validation: build, test, manual QA, and real API-path verification before publish
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.
Join the instructkr Discord — the best Korean language model community. Come chat about LLMs, harness engineering, agent workflows, and everything in between.
See the chart at the top of this README.
- This repository does not claim ownership of the original Claw Code source material.
- This repository is not affiliated with, endorsed by, or maintained by the original authors.