0xClaw
Health Warn
- License — License: MIT
- Description — Repository has a description
- Active repo — Last push 0 days ago
- Low visibility — Only 8 GitHub stars
Code Pass
- Code scan — Scanned 12 files during light audit, no dangerous patterns found
Permissions Pass
- Permissions — No dangerous permissions requested
This project is an autonomous AI agent designed to compete in coding hackathons. Given a hackathon URL, it automatically researches the requirements, generates an idea, writes the code, tests it, and submits the final project.
Security Assessment
The tool requires an external API key (stored locally in a `.env` file) and inherently relies on large language models for inference, meaning it constantly makes external network requests. Because it is an automated coding agent, it will execute local shell commands to build, test, and run projects within your environment. The automated code scan passed with no dangerous patterns, and no hardcoded secrets or dangerous system permissions were found. However, the tool's autonomous execution of generated code and shell commands presents an inherent risk. Overall risk is rated as Medium.
Quality Assessment
The repository is very recently maintained (last push was today) and is properly licensed under the permissive MIT license. As a recent hackathon winner, the tool proves its core functionality and works as advertised. However, it has very low community visibility with only 8 GitHub stars, meaning it has not been broadly tested or reviewed by the wider open-source community.
Verdict
Use with caution — the tool is safe to run locally but its autonomous code execution capabilities require strict supervision.
🦀 The first autonomous hackathon agent stop assisting and start competing (🏆 Hackathon Champion Project).
🦀 0xClaw — Autonomous AI Hackathon Competitor
🏆 1st Place Winner – Z.ai Bounty @ UK AI Agent Hackathon × OpenClaw 🦞.
Give 0xClaw a hackathon URL — it researches, codes, tests, and submits, all on its own.
⚙️ Setup
conda create -n 0xclaw python=3.11 -y
conda activate 0xclaw
pip install -e .
cp .env.example .env
./scripts/verify_setup.sh
Then fill in FLOCK_API_KEY in .env.
For a quick sanity check after installation:
python launcher/__main__.py --help
0xclaw --help
pip install -e . installs both the runtime dependencies and the local CLI in editable mode.
If you also want development tooling such as Ruff, use pip install -e .[dev].requirements.txt is kept as a compatibility mirror of the same runtime dependency set.
🚀 Launch
conda activate 0xclaw
0xclaw # interactive CLI
0xclaw --logs # with debug output
0xclaw gateway # start Telegram/other chat channels from repo config
0xclaw whatsapp login # start WhatsApp bridge and scan QR
👾 Demo Video
🔄 Pipeline
The agent runs a 7-phase pipeline to produce a complete hackathon submission.
Trigger any phase with natural language — routing is automatic.
| # | Phase | Output |
|---|---|---|
| 1 | research | hackathon/context.json |
| 2 | idea | hackathon/ideas.json |
| 3 | selection | hackathon/selected_idea.json |
| 4 | planning | hackathon/plan.md · tasks.json |
| 5 | coding | hackathon/project/ |
| 6 | testing | hackathon/test_results.json |
| 7 | doc | hackathon/submission/ |
Some prompts for quick understand the processe:
research the hackathon requirements
generate project ideas
plan the architecture
implement the project
run tests
write the documentation
⌨️ Commands
/status | Pipeline progress + session token usage |
/resume | Resume from last checkpoint |
/redo <phase> | Reset phase and all downstream, then re-run |
/new | Clear all outputs, fresh start |
/stop | Cancel running task |
/help | Show all commands |
? | Alias for /help |
!<cmd> | Run a shell command without leaving the agent (e.g. !git status) |
Long-running phases hand off to the background after the first reply — you can keep chatting while work continues.
Ctrl+C interrupts the current task but never exits — type /exit to quit.
🧠 Models
Inference powered by FLock.io and Z.AI
| Phases | Model | Context |
|---|---|---|
| research · idea · selection · doc | minimax-m2.1 | 196k |
| planning · coding · testing | minimax-m2.5 | 205k |
💬 Channels
The runtime has built-in support for 10 messaging platforms (2/10 now passed solid test). Enable any via config.json + one env var:
| $\color{#25D366}{\textbf{Telegram}}$ | Discord | Slack | Feishu | |
| DingTalk | Matrix | WeChat Work | $\color{#25D366}{\textbf{WhatsApp}}$ |
Telegram uses long polling — no public IP or webhook required.
Configure it in 0xclaw/config/config.json under channels.telegram, then run 0xclaw gateway.
WhatsApp uses a local bridge process. Configure channels.whatsapp, run 0xclaw whatsapp login to scan the QR code, then start 0xclaw gateway. Bridge assets and auth state are stored under ~/.0xclaw/.
Reviews (0)
Sign in to leave a review.
Leave a reviewNo results found