Science-Star (USTC AI4Science, 2025)
github.com/ustc-ai4science/science-starOpen-source platform for building, extending, and experimenting with scientific agents, providing modular agent construction tools and standardized evaluation pipelines for accelerating autonomous scientific discovery research (748+ stars, MIT License)
Sourced from
- GitHub — github.com/ustc-ai4science/science-star
- Awesome AI for Science — github.com/ustc-ai4science/science-star
Related resources
Open-source LLM-powered R&D agent framework automating data-driven AI solution building through automated research, development, and evolution; achieves top open-source performance on MLE-Bench with dual Researcher-Developer agents and supports research copilot, data mining, Kaggle, and quant R&D workflows (13.6K+ stars, MIT License, 2025-2026)
Evolvable and privacy-preserving multi-agent framework automating, scaling, and accelerating data sciences with a particular focus on end-to-end single-cell biology analyses; features agentic code evolution, multi-agent team orchestration, distributed architecture, and a community marketplace with 1,000+ curated agents and skills (428+ stars)
Automated hypothesis testing with agentic sequential falsifications
Autonomous algorithm discovery combining evolutionary search with peer-review reward models, achieving best-known performance on circle packing problems
Andrej Karpathy's autonomous LLM research framework: AI agent runs overnight experiments on a real training setup, auto-editing code→5min training→evaluation in a loop, ~100 experiments per night on a single GPU
Lightweight Markdown-only skills for autonomous ML research with cross-model review loops, idea discovery, and experiment automation; no framework lock-in, works with Claude Code, Codex, OpenClaw, or any LLM agent (12.8K+ stars, MIT License, 2026)