CodeScientist (AllenAI)

github.com/allenai/codescientist
Active339updated 2 months ago
Python
Apache-2.0

End-to-end semi-automated scientific discovery system that designs, iterates, and analyzes code-based experiments via LLM-as-a-mutator over scientific articles and code examples; auto-creates, runs, and debugs experiment code in containers and writes meta-analysis reports (339+ stars, Apache 2.0)

Sourced from

  • Awesome AI for Sciencegithub.com/allenai/codescientist
  • GitHubgithub.com/allenai/codescientist

Related resources

Open-source implementation of AlphaEvolve's evolutionary coding agent paradigm, enabling LLMs to autonomously discover and optimize algorithms through iterative evolution, matching the approach behind DeepMind's breakthrough matrix multiplication discovery (6.2K+ stars, 2025)

Active6.4K2 months ago
Python
Apache-2.0

Self-evolving AI scientist with 6 specialized sub-agents (plan/research/code/debug/analyze/write) and persistent memory, #1 on DeepResearch Bench II and AstaBench, supporting multi-provider LLMs and multi-channel deployment (Apache 2.0, 2026)

Active3.3K1 week ago
Python
Apache-2.0

Democratizing AI scientists by transforming any LLM into research systems with 600+ scientific tools (Harvard MIMS)

Active1.4K10 hours ago
Python
Apache-2.0

Closed-loop multi-agent system from hypothesis to verification across 12 scientific tasks, #1 on MLE-Bench (36.44%)

Active1.3K1 month ago
Python
NOASSERTION

LLM-driven machine learning engineering agent using agentic tree search to autonomously draft, debug and benchmark ML code; wins 4× more medals than the best linear agent on OpenAI's MLE-Bench (75 Kaggle competitions) (1.3K+ stars, MIT License)

Active1.3K1 month ago
Python
MIT

First system to make novel, verifiable scientific discoveries by pairing LLMs with evolutionary search, solving open problems in combinatorics (cap set problem) and discovering faster matrix multiplication algorithms

Stale1.1K2 years ago
Jupyter Notebook
Apache-2.0