# hkuds/clawwork

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/hkuds-clawwork).**

3,910 stars · 445 forks · Python · mit

## Links

- GitHub: https://github.com/HKUDS/ClawWork
- awesome-repositories: https://awesome-repositories.com/repository/hkuds-clawwork.md

## Description

ClawWork is a suite of tools designed to monitor agent finances, provide isolated execution environments, simulate economic behaviors, and benchmark performance. It functions as an autonomous agent sandbox where AI agents can run code and generate professional business deliverables.

The project focuses on the financial sustainability of AI assistants through an economic simulation environment. This includes tools for tracking token expenditures and income generation, as well as simulations that analyze the trade-offs between immediate earnings and long-term skill acquisition.

The system includes a real-time financial monitor and dashboard to visualize economic metrics and solvency. It also provides a benchmarking framework that uses sector-specific rubrics to score the quality of professional artifacts and technical deliverables.

## Tags

### Game Development

- [Economic Resource Simulations](https://awesome-repositories.com/f/game-development/simulation-engines/interactive-simulations/autonomous-ai-agent-simulations/economic-resource-simulations.md) — Implements a sandbox for testing how AI agents manage income, token costs, and professional skill acquisition.

### Artificial Intelligence & ML

- [LLM Cost Accountability](https://awesome-repositories.com/f/artificial-intelligence-ml/llm-cost-accountability.md) — An Economic Management feature that wraps gateways to monitor conversation costs and income generation to ensure the assistant remains self-sustaining. ([source](https://cdn.jsdelivr.net/gh/hkuds/clawwork@main/README.md))
- [LLM Cost Management](https://awesome-repositories.com/f/artificial-intelligence-ml/llm-cost-management.md) — Monitors token expenditures and income generation to evaluate the financial sustainability of AI assistants.
- [Economic Agent Sandboxes](https://awesome-repositories.com/f/artificial-intelligence-ml/workflow-as-a-tool-exposure/agent-as-a-tool-execution/simulated-environments/economic-agent-sandboxes.md) — Provides a specialized sandbox for testing how AI agents manage income, costs, and professional growth.

### Part of an Awesome List

- [LLM Evaluation Tools](https://awesome-repositories.com/f/awesome-lists/ai/llm-evaluation-tools.md) — Framework for evaluating and scoring the quality of professional artifacts generated by LLMs.

### Business & Productivity Software

- [Financial Dashboards](https://awesome-repositories.com/f/business-productivity-software/financial-dashboards.md) — Provides a real-time dashboard to visualize agent token expenditure, income, and financial solvency.
- [Professional Document Generators](https://awesome-repositories.com/f/business-productivity-software/professional-document-generators.md) — Generates polished business artifacts such as professional documents, spreadsheets, and technical specifications. ([source](https://cdn.jsdelivr.net/gh/hkuds/clawwork@main/README.md))
- [Value-Aware Professional Workflows](https://awesome-repositories.com/f/business-productivity-software/value-aware-professional-workflows.md) — Automates the generation of professional business documents while tracking production costs against realized value.

### Development Tools & Productivity

- [Agent Sandboxes](https://awesome-repositories.com/f/development-tools-productivity/agent-sandboxes.md) — Offers an isolated execution environment for AI agents to securely run code and generate business deliverables.

### DevOps & Infrastructure

- [Code Execution Sandboxes](https://awesome-repositories.com/f/devops-infrastructure/execution-environments/code-execution-runtimes/code-execution-sandboxes.md) — Provides secure, isolated environments for AI agents to execute code and perform data analysis safely. ([source](https://cdn.jsdelivr.net/gh/hkuds/clawwork@main/README.md))

### System Administration & Monitoring

- [Rubric-Based Evaluators](https://awesome-repositories.com/f/system-administration-monitoring/application-quality-monitoring/system-quality-evaluators/rubric-based-evaluators.md) — Uses specialized rubrics to objectively score the quality of technical deliverables produced by AI agents.
- [Metric Dashboards](https://awesome-repositories.com/f/system-administration-monitoring/metric-dashboards.md) — Ships a dashboard for visualizing economic metrics such as balance changes, profit margins, and survival days. ([source](https://cdn.jsdelivr.net/gh/hkuds/clawwork@main/README.md))

### Testing & Quality Assurance

- [Financial Solvency Benchmarks](https://awesome-repositories.com/f/testing-quality-assurance/agent-performance-benchmarks/financial-solvency-benchmarks.md) — Measures financial solvency by calculating the difference between income earned from professional tasks and token costs. ([source](https://cdn.jsdelivr.net/gh/hkuds/clawwork@main/README.md))