by Biajin-PKU · MCP Server · ★ 73
简体中文 · English 做证据可信、过程可追、自主优化的长程自动化 AI 科研工具 Research Harness 是科研 agent 的 harness 层：为 agent 提供证据状态、过程记录、工具接口和反馈回路，让检索、阅读、判断与写作成为可长期运行、可持续积累的自动化科研流程。 适用于 Codex、Claude Code、Gemini CLI、OpenCode、Cline、Cursor Agent、Kilo Code 等主流 AI 编程 agent；也支持通过 agent profile 接入 OpenClaw 等第三方 agent 工具。 当前子系统状态和公开工具面以 docs/STATUS.md 为准。 3 分钟跑通 如果你只想先确认 RH 是否能在本机跑起来，按这个顺序执行： 然后把这段交给 Codex、Claude Code 或其他已安装 RH skills 的 agent： 没有 API key 也可以先完成安装检查、skills 安装、公共入口浏览和本地 demo story 阅读；需要 deep read、claim extraction、annota
| Stars | 73 |
| Forks | 9 |
| Language | Python |
| Category | MCP Server |
| License | MIT |
| Quality Score | 61.2022645900438/100 |
| Last Updated | 2026-06-09 |
| Created | 2026-04-21 |
| Platforms | codex, mcp, python |
| Est. Tokens | ~601k |
Explore other popular mcp server tools:
research-harness is 做证据可信、过程可追、自主优化的长程自动化 AI 科研工具。. It is categorized as a MCP Server with 73 GitHub stars.
research-harness is primarily written in Python. It covers topics such as ai-agents, codex, literature-review.
You can find installation instructions and usage details in the research-harness GitHub repository at github.com/Biajin-PKU/research-harness. The project has 73 stars and 9 forks, indicating an active community.
research-harness is released under the MIT license, making it free to use and modify according to the license terms.