Best Research & science harnesses for AI agents
The most-adopted Research & science harnesses an AI agent can use, ranked by GitHub stars, with what each is best for. Loadbay is an MCP server, so an agent can pull this list live:
claude mcp add --transport http loadbay https://loadbay.xyz/api/mcp
-
1. AI-Scientist
14,000★ · Python
Most adopted — the default starting point. Best for OpenAI, Anthropic, Semantic Scholar. First end-to-end system for fully automated open-ended scientific discovery: generates ideas, runs experiments, and writes papers. -
2. STORM
14,000★ · Python
Best for OpenAI, Bing, You.com. Stanford knowledge-curation system that researches a topic via internet search and writes a full-length, cited report. -
3. paper-qa
8,722★ · Python
Best for arXiv, Semantic Scholar. High-accuracy RAG framework for answering questions from scientific papers with grounded citations. -
4. AlphaFold 3
8,200★ · Python
Best for JAX, PDB. Official DeepMind inference pipeline for AlphaFold 3, predicting joint structures of proteins, nucleic acids, ligands, and ions. -
5. AI-Scientist-v2
6,600★ · Python
Best for OpenAI, Anthropic, Semantic Scholar. Agentic successor that uses progressive tree search to autonomously generate hypotheses, run ML experiments, and write manuscripts. -
6. Boltz
4,100★ · Python
Best for PyTorch, MSA servers. Open family of biomolecular interaction models for predicting protein and complex structures and binding affinity, an AlphaFold3-class tool. -
7. zotero-mcp
3,868★ · Python
Best for Zotero. MCP server linking a Zotero research library to AI assistants for paper search, summaries, and citation analysis. -
8. Biomni
3,200★ · Python
Best for Anthropic, OpenAI, MCP. General biomedical AI agent that combines LLM reasoning, retrieval-augmented planning, and code execution over a biomedical toolbox. -
9. arxiv-mcp-server
2,900★ · Python
Best for arXiv. An MCP server for searching and analyzing arXiv papers, so a research agent can pull and read the literature. -
10. ESM3
2,200★ · Python
Best for PyTorch, HuggingFace. EvolutionaryScale flagship protein language models (ESM3, ESM C) reasoning jointly over sequence, structure, and function.