by InternScience · Agent Tool · ★ 44
🔬 ResearchHarness A lightweight, general-purpose harness for tool-using LLM agents. ResearchHarness is a foundational harness for running tool-using LLM agents on real local and web tasks. It is designed to be general, stable, fair, lightweight, and feature-complete. It serves three practical roles: a fair execution substrate for agent benchmarks such as ResearchClawBench a reference baseline and meta harness for future harness optimization a l
| Stars | 44 |
| Forks | 16 |
| Language | Python |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 62.5306246377127/100 |
| Open Issues | 4 |
| Last Updated | 2026-07-16 |
| Created | 2026-03-31 |
| Platforms | gemini, python |
| Est. Tokens | ~25k |
These tools work well together with ResearchHarness for enhanced workflows:
Explore other popular agent tool tools:
ResearchHarness is A lightweight, general-purpose harness for tool-using LLM agents, fair benchmark evaluation, harness baselines, and personal assistant workflows.. It is categorized as a Agent Tool with 44 GitHub stars.
ResearchHarness is primarily written in Python. It covers topics such as agent, agent-harness, assistant.
You can find installation instructions and usage details in the ResearchHarness GitHub repository at github.com/InternScience/ResearchHarness. The project has 44 stars and 16 forks, indicating an active community.
ResearchHarness is released under the MIT license, making it free to use and modify according to the license terms.