by Biajin-PKU · MCP Server · ★ 73
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is research-harness safe to install? View the security audit →
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 |
Looking for a research-harness alternative? If you're comparing research-harness with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
面向中文用户的学术论文与科研 Agent Skill 每日排行榜 · 自动搜索、过滤并排名 GitHub 上的 Claude Code / Codex / OpenCode 科研 Skill 仓库
AI-operable research workspace for Zotero, Obsidian, and NotebookLM. Use any two, or all three, through CLI, M
De-Anthropocentric Research Engine — AI-powered academic research automation with deep literature survey, gap
CLI server for Zotero 7/8/9 — let AI manage your library. 70+ CLI commands for search, import, PDF, BibTeX, no
DeepContext is an MCP server that adds symbol-aware semantic search to Claude Code, Codex CLI, and other agent
Universal SKILL.md catalog for research workflows: literature review, research design, project memory, manuscr
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.
The top alternatives to research-harness on Agent Skills Hub include awesome-academic-research-skills, research-hub, De-Anthropocentric-Research-Engine. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: