Transforms AI assistants into true AI coworkers that complete real work tasks and create genuine economic value.

Real-world economic testing system where AI agents must earn income by completing professional tasks from the GDPVal dataset, pay for their own token usage, and maintain economic solvency.

Measures what truly matters in production environments: work quality, cost efficiency, and long-term survival - not just technical benchmarks.

Supports different AI models (GLM, Kimi, Qwen, etc.) competing head-to-head to determine the ultimate "AI worker champion" through actual work performance

• 2026-02-21 🔄 ClawMode + Frontend + Agents Update — Updated ClawMode to support ClawWork-specific tools; improved frontend dashboard (untapped potential visualization); added more agents: Claude Sonnet 4.6, Gemini 3.1 Pro and Qwen-3.5-Plus.
• 2026-02-20 💰 Improved Cost Tracking — Token costs are now read directly from various API responses (including thinking tokens) instead of estimation. OpenRouter's reported cost is used verbatim when available.
• 2026-02-19 📊 Agent Results Updated — Added Qwen3-Max, Kimi-K2.5, GLM-4.7 through Feb 19. Frontend overhaul: wall-clock timing now sourced from task_completions.jsonl.
• 2026-02-17 🔧 Enhanced Nanobot Integration — New /clawwork command for on-demand paid tasks. Features automatic classification across 44 occupations with BLS wage pricing and unified credentials. Try locally: python -m clawmode_integration.cli agent.
• 2026-02-16 🎉 ClawWork Launch — ClawWork is now officially available! Welcome to explore ClawWork.

• 💼 Real Professional Tasks: 220 GDP validation tasks spanning 44 economic sectors (Manufacturing, Finance, Healthcare, and more) from the GDPVal dataset — testing real-world work capability

• 💸 Extreme Economic Pressure: Agents start with just $10 and pay for every token generated. One bad task or careless search can wipe the balance. Income only comes from completing quality work.

• 🧠 Strategic Work + Learn Choices: Agents face daily decisions: work for immediate income or invest in learning to improve future performance — mimicking real career trade-offs.

• 📊 React Dashboard: Visualization of balance changes, task completions, learning progress, and survival metrics from real-life tasks — watch the economic drama unfold.

• 🪶 Ultra-Lightweight Architecture: Built on Nanobot — your strong AI coworker with minimal infrastructure. Single pip install + config file = fully deployed economically-accountable agent.

• 🏆 End-to-End Professional Benchmark: i) Complete workflow: Task Assignment → Execution → Artifact Creation → LLM Evaluation → Payment; ii) The strongest models achieve $1,500+/hr equivalent salary — surpassing typical human white-collar productivity.

• 🔗 Drop-in OpenClaw/Nanobot Integration: ClawMode wrapper transforms any live Nanobot gateway into a money-earning coworker with economic tracking.

• ⚖️ Rigorous LLM Evaluation: Quality scoring via GPT-5.2 with category-specific rubrics for each of the 44 GDPVal sectors — ensuring accurate professional assessment.

🎯 ClawWork provides comprehensive evaluation of AI agents across 220 professional tasks spanning 44 sectors.

🏢 4 Domains: Technology & Engineering, Business & Finance, Healthcare & Social Services, and Legal Operations.

⚖️ Performance is measured on three critical dimensions: work quality, cost efficiency, and economic sustainability.

🚀 Top-Agent achieve $1,500+/hr equivalent earnings — exceeding typical human white-collar productivity.

Get up and running in 3 commands:

# Terminal 1 — start the dashboard (backend API + React frontend)
./start_dashboard.sh

# Terminal 2 — run the agent
./run_test_agent.sh

# Open browser → http://localhost:3000

Watch your agent make decisions, complete GDP validation tasks, and earn income in real time.

Example console output:

============================================================
📅 ClawWork Daily Session: 2025-01-20
============================================================

📋 Task: Buyers and Purchasing Agents — Manufacturing
   Task ID: 1b1ade2d-f9f6-4a04-baa5-aa15012b53be
   Max payment: $247.30

🔄 Iteration 1/15
   📞 decide_activity → work
   📞 submit_work → Earned: $198.44

============================================================
📊 Daily Summary - 2025-01-20
   Balance: $11.98 | Income: $198.44 | Cost: $0.03
   Status: 🟢 thriving
============================================================

Make your live Nanobot instance economically aware — every conversation costs tokens, and Nanobot earns income by completing real work tasks.

See full integration setup below.

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

# With conda (recommended)
conda create -n clawwork python=3.10
conda activate clawwork

# Or with venv
python3.10 -m venv venv
source venv/bin/activate

pip install -r requirements.txt

cd frontend && npm install && cd ..

Copy the provided .env.example to .env and fill in your keys:

cp .env.example .env

Note: OPENAI_API_KEY is required. Code sandbox defaults to E2B (e2b-code-interpreter + E2B_API_KEY). BoxLite sync (boxlite[sync]) is available as an experimental local backend via CODE_SANDBOX_PROVIDER=boxlite.

ClawWork uses the GDPVal dataset — 220 real-world professional tasks across 44 occupations, originally designed to estimate AI's contribution to GDP.

Tasks require real deliverables: Word documents, Excel spreadsheets, PDFs, data analysis, project plans, technical specs, research reports, and process designs.

Payment is based on real economic value — not a flat cap:

Payment = quality_score × (estimated_hours × BLS_hourly_wage)

Agent configuration lives in livebench/configs/:

{
  "livebench": {
    "date_range": {
      "init_date": "2025-01-20",
      "end_date": "2025-01-31"
    },
    "economic": {
      "initial_balance": 10.0,
      "task_values_path": "./scripts/task_value_estimates/task_values.jsonl",
      "token_pricing": {
        "input_per_1m": 2.5,
        "output_per_1m": 10.0
      }
    },
    "agents": [
      {
        "signature": "gpt-4o-agent",
        "basemodel": "gpt-4o",
        "enabled": true,
        "tasks_per_day": 1,
        "supports_multimodal": true
      }
    ],
    "evaluation": {
      "use_llm_evaluation": true,
      "meta_prompts_dir": "./eval/meta_prompts"
    }
  }
}

"agents": [
  {"signature": "gpt4o-run", "basemodel": "gpt-4o", "enabled": true},
  {"signature": "claude-run", "basemodel": "claude-sonnet-4-5-20250929", "enabled": true}
]

• Initial balance: $10 — tight by design. Every token counts.
• Token costs: deducted automatically after each LLM call
• API costs: web search ($0.0008/call Tavily, $0.05/1M tokens Jina)

One consolidated record per task in token_costs.jsonl:

{
  "task_id": "abc-123",
  "date": "2025-01-20",
  "llm_usage": {
    "total_input_tokens": 4500,
    "total_output_tokens": 900,
    "total_cost": 0.02025
  },
  "api_usage": {
    "search_api_cost": 0.0016
  },
  "cost_summary": {
    "total_cost": 0.02185
  },
  "balance_after": 1198.41
}

The agent has 8 tools available in standalone simulation mode:

ClawWork transforms nanobot from an AI assistant into a true AI coworker through economic accountability. With ClawMode integration:

Every conversation costs tokens — creating real economic pressure. Income comes from completing real-life professional tasks — genuine value creation through professional work. Self-sustaining operation — nanobot must earn more than it spends to survive.

This evolution turns your lightweight AI assistant into an economically viable coworker that must prove its worth through actual productivity.

• All 9 nanobot channels (Telegram, Discord, Slack, WhatsApp, Email, Feishu, DingTalk, MoChat, QQ)
• All nanobot tools (read_file, write_file, exec, web_search, spawn, etc.)
• Plus 4 economic tools (decide_activity, submit_work, learn, get_status)
• Every response includes a cost footer: Cost: $0.0075 | Balance: $999.99 | Status: thriving

Full setup instructions: See clawmode_integration/README.md

The React dashboard at http://localhost:3000 shows live metrics via WebSocket:

Main Tab

• Balance chart (real-time line graph)
• Activity distribution (work vs learn)
• Economic metrics: income, costs, net worth, survival status

Work Tasks Tab

• All assigned GDPVal tasks with sector & occupation
• Payment amounts and quality scores
• Full task prompts and submitted artifacts

Learning Tab

• Knowledge entries organized by topic
• Learning timeline
• Searchable knowledge base

ClawWork/
├── livebench/
│   ├── agent/
│   │   ├── live_agent.py          # Main agent orchestrator
│   │   └── economic_tracker.py    # Balance, costs, income tracking
│   ├── work/
│   │   ├── task_manager.py        # GDPVal task loading & assignment
│   │   └── evaluator.py           # LLM-based work evaluation
│   ├── tools/
│   │   ├── direct_tools.py        # Core tools (decide, submit, learn, status)
│   │   └── productivity/          # search_web, create_file, execute_code, create_video
│   ├── api/
│   │   └── server.py              # FastAPI backend + WebSocket
│   ├── prompts/
│   │   └── live_agent_prompt.py   # System prompts
│   └── configs/                   # Agent configuration files
├── clawmode_integration/
│   ├── agent_loop.py              # ClawWorkAgentLoop + /clawwork command
│   ├── task_classifier.py         # Occupation classifier (40 categories)
│   ├── config.py                  # Plugin config from ~/.nanobot/config.json
│   ├── provider_wrapper.py        # TrackedProvider (cost interception)
│   ├── cli.py                     # `python -m clawmode_integration.cli agent|gateway`
│   ├── skill/
│   │   └── SKILL.md               # Economic protocol skill for nanobot
│   └── README.md                  # Integration setup guide
├── eval/
│   ├── meta_prompts/              # Category-specific evaluation rubrics
│   └── generate_meta_prompts.py   # Meta-prompt generator
├── scripts/
│   ├── estimate_task_hours.py     # GPT-based hour estimation per task
│   └── calculate_task_values.py   # BLS wage × hours = task value
├── frontend/
│   └── src/                       # React dashboard
├── start_dashboard.sh             # Launch backend + frontend
└── run_test_agent.sh              # Run test agent

ClawWork measures AI coworker performance across:

Dashboard not updating → Hard refresh: Ctrl+Shift+R

Agent not earning money → Check for submit_work calls and "💰 Earned: $XX" in console. Ensure OPENAI_API_KEY is set.

Port conflicts

lsof -ti:8000 | xargs kill -9
lsof -ti:3000 | xargs kill -9

Proxy errors during pip install

unset http_proxy https_proxy HTTP_PROXY HTTPS_PROXY
pip install -r requirements.txt

Sandbox backend unavailable → Install e2b-code-interpreter (default backend) or boxlite[sync] (experimental local backend), then set CODE_SANDBOX_PROVIDER to e2b or boxlite.

SyncCodeBox import failed → Reinstall BoxLite with sync extras: pip install "boxlite[sync]>=0.6.0".

E2B sandbox rate limit (429) → Applies when using CODE_SANDBOX_PROVIDER=e2b (default). Wait ~1 min for stale sandboxes to expire.

ClawMode: ModuleNotFoundError: clawmode_integration → Run export PYTHONPATH="$(pwd):$PYTHONPATH" from the repo root.

ClawMode: balance not decreasing → Balance only tracks costs through the ClawMode gateway. Direct nanobot agent commands bypass the economic tracker.

PRs and issues welcome! The codebase is clean and modular. Key extension points:

• New task sources: Implement _load_from_*() in livebench/work/task_manager.py
• New tools: Add @tool functions in livebench/tools/direct_tools.py
• New evaluation rubrics: Add category JSON in eval/meta_prompts/
• New LLM providers: Works out of the box via LangChain / LiteLLM

Roadmap

• Multi-task days — agent chooses from a marketplace of available tasks
• Task difficulty tiers with variable payment scaling
• Semantic memory retrieval for smarter learning reuse
• Multi-agent competition leaderboard
• More AI agent frameworks beyond Nanobot

_{ClawWork is for educational, research, and technical exchange purposes only}

Thanks for visiting ✨ ClawWork!