Home / Open Source / ClawWork

ClawWork

ClawWork transforms AI assistants into economically accountable AI coworkers that complete real professional tasks, earn income, and compete across 220 GDP-validated tasks spanning 44 industry sectors.

PythonMITAgent
โญ GitHubhttps://github.com/HKUDS/ClawWork
8,298
Stars
+84
Star growth
Mar 3, 2026
Last updated
2,369
Clicks

ClawWork: OpenClaw as Your AI Coworker

๐Ÿ’ฐ $10K earned in 7 Hours โ€” A real-world economic benchmark for AI agents

GitHub: https://github.com/HKUDS/ClawWork
Live Demo: https://hkuds.github.io/ClawWork/
Organization: HKUDS (Hong Kong University of Science and Technology Data Systems Lab)


๐Ÿง  What is ClawWork?

ClawWork is an open-source framework that transforms AI assistants into economically accountable AI coworkers. Rather than simply measuring AI on traditional benchmarks (accuracy, MMLU, reasoning scores), ClawWork asks a more practical question:

Can an AI agent actually earn money doing real professional work?

AI agents are placed into a simulated professional economy where they must:

  • Complete real-world tasks across 44 occupational sectors
  • Pay for their own token usage from a starting budget of just $10
  • Earn income based on the quality of their delivered work
  • Survive economically by maintaining a positive balance

This creates a uniquely realistic evaluation framework where the stakes are tangible and performance is measured in dollars, not just percentages.


๐Ÿš€ Key Features

๐Ÿ’ผ Real Professional Task Benchmark (GDPVal)

ClawWork is powered by the GDPVal dataset โ€” 220 real-world professional tasks across 44 occupational sectors originally designed by OpenAI to estimate AI's contribution to GDP. Task categories include:

Domain Example Occupations
Technology & Engineering Computer/IS Managers, Production Supervisors
Business & Finance Financial Analysts, Auditors, Compliance Officers
Healthcare & Social Services Social Workers, Health Administrators
Legal, Media & Operations Administrative Managers, Customer Service

Each task requires tangible deliverables: Word documents, Excel spreadsheets, PDFs, data analysis, project plans, research reports, and technical specifications.

๐Ÿ’ธ Extreme Economic Pressure

  • Agents start with only $10 in their account
  • Every LLM token call costs real money (deducted automatically)
  • Income is only earned upon completing quality-verified work
  • A single careless API call or poor task submission can bankrupt the agent
  • The payment formula mirrors real-world economics:
    Payment = quality_score ร— (estimated_hours ร— BLS_hourly_wage)

๐Ÿ† Multi-Model Competition Arena

ClawWork supports head-to-head competition between different AI models simultaneously โ€” GPT-4o, Claude Sonnet, Gemini Pro, Qwen, Kimi, GLM, and more. Results are tracked on a live leaderboard at https://hkuds.github.io/ClawWork/.

Top-performing agents achieve $1,500+/hour equivalent earnings, surpassing typical human white-collar productivity.

๐Ÿชถ Ultra-Lightweight Architecture

Built on Nanobot, ClawWork requires minimal setup:

pip install -r requirements.txt
cp .env.example .env  # Fill in API keys
./start_dashboard.sh  # Launch dashboard
./run_test_agent.sh   # Run agent

๐Ÿ“Š React Dashboard

A real-time React dashboard at http://localhost:3000 visualizes:

  • Live balance changes (line graph)
  • Activity distribution (work vs. learn decisions)
  • Task completions with quality scores and payment amounts
  • Learning knowledge base
  • Survival metrics and economic status

โš™๏ธ How It Works

Agent Decision Loop

Each "day" in the simulation, the agent faces a binary strategic decision:

  1. Work โ€” Accept and complete a professional task for income
  2. Learn โ€” Study and store knowledge to improve future performance

This mirrors real career trade-offs and introduces strategic depth beyond simple task completion.

Agent Tools (8 Available)

Tool Description
decide_activity Choose work or learn for the session
submit_work Submit completed artifacts for evaluation + payment
learn Persist domain knowledge to memory (min 200 chars)
get_status Check current balance, costs, and survival tier
search_web Search via Tavily or Jina AI
create_file Generate .txt, .xlsx, .docx, .pdf files
execute_code Run Python in an isolated E2B cloud sandbox
create_video Generate MP4 from structured slide data

Evaluation Pipeline

Work quality is scored by GPT-5.2 using category-specific rubrics for each of the 44 GDPVal occupation sectors, ensuring accurate professional-grade assessment.

Economic Tracking

All costs are tracked granularly in token_costs.jsonl:

{
  "task_id": "abc-123",
  "llm_usage": { "total_cost": 0.02025 },
  "api_usage": { "search_api_cost": 0.0016 },
  "cost_summary": { "total_cost": 0.02185 },
  "balance_after": 1198.41
}

๐Ÿ”ง Architecture Overview

ClawWork/
โ”œโ”€โ”€ livebench/
โ”‚   โ”œโ”€โ”€ agent/          # Main agent orchestrator + economic tracker
โ”‚   โ”œโ”€โ”€ work/           # Task manager + LLM-based evaluator
โ”‚   โ”œโ”€โ”€ tools/          # Core tools + productivity tools
โ”‚   โ”œโ”€โ”€ api/            # FastAPI backend + WebSocket for live updates
โ”‚   โ””โ”€โ”€ configs/        # Agent configuration files
โ”œโ”€โ”€ clawmode_integration/
โ”‚   โ”œโ”€โ”€ agent_loop.py   # ClawWorkAgentLoop with /clawwork command
โ”‚   โ”œโ”€โ”€ task_classifier.py  # Classifies tasks across 40 categories
โ”‚   โ””โ”€โ”€ provider_wrapper.py # TrackedProvider for cost interception
โ”œโ”€โ”€ eval/
โ”‚   โ””โ”€โ”€ meta_prompts/   # Category-specific evaluation rubrics
โ”œโ”€โ”€ frontend/           # React dashboard (TypeScript)
โ””โ”€โ”€ scripts/            # Task value estimation scripts

๐Ÿ”— Nanobot Integration (ClawMode)

ClawWork can be plugged into a live Nanobot instance to create an economically aware AI assistant. With ClawMode:

  • Every conversation response costs tokens from the real budget
  • The /clawwork command triggers paid professional task execution
  • Supports all 9 Nanobot channels: Telegram, Discord, Slack, WhatsApp, Email, Feishu, DingTalk, MoChat, QQ
  • Every response includes a cost footer:
    Cost: $0.0075 | Balance: $999.99 | Status: thriving

๐Ÿ“ˆ Benchmark Metrics

ClawWork evaluates AI coworkers across 8 dimensions:

Metric Description
Survival days How long the agent stays economically solvent
Final balance Net economic result at end of simulation
Total work income Gross earnings from all completed tasks
Profit margin (income - costs) / costs
Work quality Average quality score (0.0 โ€“ 1.0)
Token efficiency Income earned per dollar spent on tokens
Activity mix Percentage of work vs. learn decisions
Task completion rate Tasks completed vs. tasks assigned

๐Ÿ› ๏ธ Quick Setup

Prerequisites

  • Python โ‰ฅ 3.10
  • Node.js (for React dashboard)
  • OpenAI API Key (required)
  • E2B API Key (required for code execution)
  • Tavily or Jina API Key (optional, for web search)

Installation

git clone https://github.com/HKUDS/ClawWork.git
cd ClawWork

# Python environment
conda create -n clawwork python=3.10
conda activate clawwork
pip install -r requirements.txt

# Frontend
cd frontend && npm install && cd ..

# Configure environment
cp .env.example .env
# Edit .env with your API keys

Running

# Terminal 1 โ€” Dashboard
./start_dashboard.sh

# Terminal 2 โ€” Agent
./run_test_agent.sh

# Open http://localhost:3000

๐Ÿ“œ License

MIT License โ€” for educational, research, and technical exchange purposes.


๐ŸŒŸ Community