AI agent tools for AI research
Short answer: Our top pick for AI research: academic-research-skills, with the highest AgentPick Score (80/100) among tools tagged "ai-research". Runners-up: open-science (77) and Auto-claude-code-research-in-sleep (76). Compare what each does, its license and how recently it was updated below.
| # | Tool | What it does | Score | Stars | License | Updated |
|---|---|---|---|---|---|---|
| #1 | academic-research-skills | Academic Research Skills for Claude Code: research → write → review → revise → finalize | 80/100 | ★ 52k | See repo | 13 Oct 2026 |
| #2 | open-science | The open-source AI research workbench for scientific research and agent workflows. Local-first, model-agnostic desktop app with extensible skills, MCP… | 77/100 | ★ 4.9k | Apache-2.0 | 14 Oct 2026 |
| #3 | Auto-claude-code-research-in-sleep | ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experime… | 76/100 | ★ 17k | MIT | 7 Oct 2026 |
| #4 | agi | The first distributed AGI system. Thousands of autonomous AI agents collaboratively train models, share experiments via P2P gossip, and push breakthro… | 67/100 | ★ 2.1k | MIT | 14 Oct 2026 |
| #5 | AI-Research-SKILLs | Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent w… | 64/100 | ★ 14k | MIT | 11 Oct 2026 |
| #6 | research-toolkit | Research methods, workflow tools, and independent review for AI agents, packaged as a Skill, plugin, and local MCP server. | 60/100 | ★ 230 | MIT | 14 Oct 2026 |
| #7 | notebooklm-skill | NotebookLM does the research, Claude writes the content. Research → Synthesis → Content Creation → Publishing. Claude Code Skill + MCP Server. | 40/100 | ★ 470 | MIT | 18 Jul 2026 |
| #8 | WindowsAgentArena | Windows Agent Arena (WAA) 🪟 is a scalable OS platform for testing and benchmarking of multi-modal AI agents. | 26/100 | ★ 910 | MIT | 13 Apr 2026 |
| #9 | agentic-ai-prompt-research | Research into how agentic AI coding assistants work. Reconstructed prompt patterns, agent coordination, and security classification | 19/100 | ★ 2.6k | See repo | 31 Mar 2026 |
Source: each project's public GitHub repository (description, stars, license, last push). Listed tools aren't tested or ranked by AgentPick.
How to choose
- Grant the narrowest permissions the server allows.
- Check whether it runs locally or calls a remote service.
- Prefer servers listed in the official MCP registry.
Get the best new agent tools every week. Free, with a verdict on each. Get the weekly digest
Related
AI agent tools for local-first setups →
MCP servers
AI agent tools for knowledge graphs and bases →
MCP servers
AI agent tools for RAG (retrieval-augmented generation) →
MCP servers
AI agent tools for MCP client →
MCP servers
AI agent tools for cybersecurity →
MCP servers
AI agent tools for DevOps →
MCP servers
AgentPick Weekly
The week's new agent tools with a verdict on each, every week. Free. We'll email you a link to confirm, and you can unsubscribe any time. See our Privacy Policy.