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 →
| Stars | 73 |
| Forks | 9 |
| Language | Python |
| Category | MCP Server |
| License | MIT |
| Quality Score | 61/100 |
| Last Updated | 2026-06-09 |
| Created | 2026-04-21 |
| Platforms | codex, mcp, python |
| Est. Tokens | ~601k |
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...
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
Turn any AI agent into a research co-scientist: 280+ open-source agent skills for literature reviews, hypothes
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
An open-source research system for autonomous investigation, recursive self-improvement, and human–AI collabor
Explore other popular mcp server tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. 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: