Find open-source science resources

Local-first autonomous research system implementing a Git-like research protocol for long-running scientific discovery; explores competing explanations, executes experiments inside an isolation boundary, self-criticizes results, and exports the entire path as typed Agent-Native Research Artifacts (ARA) with exploration DAGs, claim-to-evidence anchors, content hashes, and re-execution hooks (126+ stars, Apache 2.0, arXiv 2026)

Modular framework for AI-driven scientific and algorithmic discovery, providing a unified interface for implementing, running, and fairly comparing discovery algorithms across 200+ optimization tasks; introduces AdaEvolve and EvoX adaptive/evolutionary algorithms and natively supports OpenEvolve, GEPA, and Harbor-format benchmarks (skydiscover-ai, 568+ stars, Apache 2.0, 2026)

Semi-autonomous AI scientist for scientific theory discovery and verifiable goal solving, using adversarial review-refinement loops and evolution-inspired candidate populations; integrates with Claude Code, Gemini CLI, Antigravity, and Codex harnesses (Imbue, 31+ stars, AGPL-3.0, 2026)

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)

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)

Agent skills (SKILL.md + deterministic tools) for the AI4S workflow — topic exploration, literature survey, runnable experiments, publication-grade papers, and integrity audit, with every citation and number traceable to its source (by ai4s-research, maintainers of this list; MIT, 2026)

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

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)

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)

Language agent gymnasium for challenging scientific tasks including DNA manipulation, literature search, and protein engineering

Principle-first scientific idea discovery framework that extracts reusable principles from public literature and private research materials, composes them into traceable Idea Cards with prior-art comparisons, and exports validation-ready research packs; emphasizes inspectable scientific objects, risk disclosure, and falsification paths (ICML 2026, 411+ stars, MIT License)

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)

Foundation AutoResearch Operating System: blueprint-driven runtime for orchestrating AI research workflows from idea generation and experiments to paper writing and peer review (OpenNSWM-Lab, 2.4K+ stars, 2026)

AI co-author covering the entire research lifecycle — from an under-specified research direction to a published paper; includes ResearchStudio-Idea for evidence-grounded research ideation and ResearchStudio-Reel for turning finished papers into posters, narrated videos, blogs, and interactive reels; runs as skills on Claude Code and Codex (1.2K+ 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)

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)

Fully autonomous research from idea to paper with multi-agent debate, citation verification, and OpenClaw integration (11K+ stars, 2026)

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)

Autonomous multi-agent AI scientist that mirrors a PhD workflow: literature review → grounded hypothesis → real ML experiments → self-critique → write-up; features a deterministic harness with frozen-metric scoring, edit allowlists, and a verified registry to make reward-hacking and hallucination impossible, plus 108 unit tests runnable without API keys or GPUs (461+ stars, MIT License, 2026)

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

Foundational auto-research agent framework for agentic science at scale, providing modular agent construction, run-level self-evolution, and multiple SciMaster domain agents (ML-Master, X-Master, Browse-Master); outperforms general-purpose agents across authoritative benchmarks including the OpenAI Frontier Science Benchmark (206+ stars, Apache 2.0, 2026)

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)

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

FutureHouse's end-to-end scientific discovery multi-agent system orchestrating literature search (Crow/Falcon) and data analysis (Finch) agents, first AI-generated drug discovery identifying ripasudil as novel dry AMD therapeutic (2025)

Extended autonomy AI scientist with 200 parallel agent rollouts, 42K lines of code execution, 1.5K papers analyzed per run, achieving 79.4% accuracy and 7 scientific discoveries (Edison Scientific)

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

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)

Universal scientific research intelligence covering 50+ disciplines, repositioning LLMs as cross-disciplinary generators with human experts as verifiers; 30B model outperforms Claude Opus and GPT on 5 research benchmarks

Open-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)

Scientific equation discovery with agentic AI, elevating LLMs from equation proposers to autonomous scientists that write code, analyze data, implement equations, and optimize based on experimental feedback; outperforms baselines by 6-35% across four science disciplines with robustness to noise and out-of-domain generalization (GAIR-NLP / SJTU, 49+ stars, Apache 2.0)

Official implementation of the second-generation fully autonomous scientific discovery system, extending the original with agentic tree search and reduced template dependency to achieve workshop-level accepted papers (6.7K+ stars, 2025)

Autonomous multi-agent research loop for model architecture discovery that ran 1,773 experiments over 20,000 GPU hours and produced 106 state-of-the-art linear-attention architectures, surpassing human-designed baselines including Mamba2 and DeltaNet (1.1K+ stars, Apache 2.0)

Autonomous algorithm discovery combining evolutionary search with peer-review reward models, achieving best-known performance on circle packing problems

Autonomous pipeline from literature review→hypothesis→algorithm implementation→publication-level writing with Scientist-Bench evaluation

Automated and rigorous experiments using AI agents for scientific discovery

Automated hypothesis testing with agentic sequential falsifications