ToolUniverse

Decentralized self-organizing teams of AI agents for long-running computational scientific experimentation; agents critique each other's proposals before spending compute and share successes/failures to avoid redundant exploration, achieving +8.33% on BioML-Bench, 1.9× faster nanoGPT optimization, and +12.5% on ProteinGym ACE2-Spike (425+ stars, 2026)

End-to-end autonomous AI research engine that turns an idea into a complete LaTeX paper by dispatching real computational experiments to local GPUs or SLURM clusters, collecting actual results, generating figures/tables, and writing a data-grounded manuscript rather than LLM hallucinations (OpenRaiser, 1.5K+ stars, MIT License, 2026)

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)

Generalist autonomous research agent that grows a hypothesis tree to optimize any measurable task, beating Claude Code and Codex by 2.5× on the same compute budget across BrowseComp, Terminal-Bench 2.0, math reasoning, and MLE-Bench Lite; supports native CLI, keyless Claude Code/Codex integration, and an MCP tool server (RUC-NLPIR, 866+ stars, Apache 2.0, 2026)

Robust, lightweight infrastructure for multi-agent autonomous self-evolution, built for autoresearch; agents run in isolated git worktrees, share knowledge through a common state directory, and are scored by a grader daemon; natively integrated with Claude Code, Codex, Cursor Agent, OpenCode, and Kiro (672+ stars, Apache 2.0)

First fully customizable open-source multiagent framework automating complete research lifecycle from idea conception to LaTeX papers with dynamic workflows