by ProjectDXAI · Agent Tool · ★ 166
labrat English | 简体中文 is a local-first runtime that puts Claude Code or Codex on a real research problem with a scoreboard and enough structure to run for hours. Population search, not single-thread: families of ideas compete for compute budget, and the ones that produce real signal earn more room to keep going. Live example run: the baseline still leads on the main selection metric, while has already won two decisive held-out challenges and earned extra funding. treats Claude Code and Codex as peer operator interfaces.
| Stars | 166 |
| Forks | 6 |
| Language | Python |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 65.5809497095132/100 |
| Last Updated | 2026-04-24 |
| Created | 2026-03-30 |
| Platforms | claude-code, python |
| Est. Tokens | ~114k |
These tools work well together with labrat for enhanced workflows:
Explore other popular agent tool tools:
labrat is Autonomous multi-branch research lab. Branches compete for compute budget. The system converges on what works.. It is categorized as a Agent Tool with 166 GitHub stars.
labrat is primarily written in Python. It covers topics such as ai-agents, autonomous-research, claude-code.
You can find installation instructions and usage details in the labrat GitHub repository at github.com/ProjectDXAI/labrat. The project has 166 stars and 6 forks, indicating an active community.
labrat is released under the MIT license, making it free to use and modify according to the license terms.