Science & lab agents
Science and lab agents carry out scientific work itself: running experiments, generating hypotheses, and drafting papers. AI-Scientist automates open-ended discovery end to end, while autoresearch runs nanochat training experiments on a single GPU without a human in the loop.
1,137 agents · most starred first
Top 100 of 1,137
AI agents running research on single-GPU nanochat training automatically
Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 250,000+ scientists worldwide. 177 ready-to-use validated skills plus 100+ scientific databases covering biology, chemistry, medicine, and drug discovery. Compatible with Cursor, Claude Code, Codex, Pi, Antigravity, and the open Agent Skills standard.
Google Research
Research and development (R&D) is crucial for the enhancement of industrial productivity, especially in the AI era, where the core aspects of R&D are mainly focused on data and models. We are committed to automating these high-value generic R&D processes through R&D-Agent, which lets AI drive data-driven AI. 🔗https://aka.ms/RD-Agent-Tech-Report
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑🔬
The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search
🤖📐专为数学建模设计的 Agent & skills ,自动完成数学建模,生成一份完整的可以直接提交的论文。 An Agent Designed for Mathematical Modeling ,Automatically complete mathmodel and generate a complete paper ready for submission.
The open-source AI research workbench for scientific research and agent workflows. Local-first, model-agnostic desktop app with extensible skills, MCP tools and connectors, Python/R execution and traceable artifacts for reproducible research on macOS, Windows and Linux.
🔬 Harness Vibe Research with Self-evolving AI Scientists
The open-source AI workbench for scientific research
Biomni: a general-purpose biomedical AI agent
RNA vaccines have become a key tool in moving forward through the challenges raised both in the current pandemic and in numerous other public health and medical challenges. With the rollout of vaccines for COVID-19, these synthetic mRNAs have become broadly distributed RNA species in numerous human populations. Despite their ubiquity, sequences are not always available for such RNAs. Standard methods facilitate such sequencing. In this note, we provide experimental sequence information for the RNA components of the initial Moderna (https://pubmed.ncbi.nlm.nih.gov/32756549/) and Pfizer/BioNTech (https://pubmed.ncbi.nlm.nih.gov/33301246/) COVID-19 vaccines, allowing a working assembly of the former and a confirmation of previously reported sequence information for the latter RNA. Sharing of sequence information for broadly used therapeutics has the benefit of allowing any researchers or clinicians using sequencing approaches to rapidly identify such sequences as therapeutic-derived rather than host or infectious in origin. For this work, RNAs were obtained as discards from the small portions of vaccine doses that remained in vials after immunization; such portions would have been required to be otherwise discarded and were analyzed under FDA authorization for research use. To obtain the small amounts of RNA needed for characterization, vaccine remnants were phenol-chloroform extracted using TRIzol Reagent (Invitrogen), with intactness assessed by Agilent 2100 Bioanalyzer before and after extraction. Although our analysis mainly focused on RNAs obtained as soon as possible following discard, we also analyzed samples which had been refrigerated (~4 ℃) for up to 42 days with and without the addition of EDTA. Interestingly a substantial fraction of the RNA remained intact in these preparations. We note that the formulation of the vaccines includes numerous key chemical components which are quite possibly unstable under these conditions-- so these data certain
GDM Science Skills to speed up agentic scientific workflows with better grounding and higher token efficiency. Integrate insights from AlphaGenome, AFDB, UniProt and 30+ other databases and tools.
Formal verification for AI: a Lean 4 + Dafny proof checker that catches fake AI proofs (reward hacking), and verified recursive self-improvement (RSI) for coding agents. AI for math, physics and software engineering.
Open Science Desktop — local-first, model-agnostic AI research workbench for macOS, Windows & Linux. Open-source Claude Science desktop alternative built on Tauri + MCP + agent skills.
Democratizing AI scientists with ToolUniverse
Turn any AI agent into a computational researcher. HexStellar Cortex delivers software-accelerated optimization, quantum computing, scientific computing, decision intelligence, and verifiable execution through a Python CLI and API—with certainty labels, verification receipts, examples, and a free sandbox. Start instantly: pip install hexstellar
InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery
An AI co-scientist running on your desktop. Claude Science but better.
AgentSociety 2 is a modern, LLM-native agent simulation platform designed for social science research and experimental design. It provides a flexible framework for creating and managing intelligent agents in simulated environments.
🦖 ClawBio - The first bioinformatics-native AI agent skill library. Local-first. Reproducible. Open. Free.
🔥 An autonomous AI agent that runs your deep learning experiments 24/7 while you sleep. Zero-cost monitoring, Leader-Worker architecture, constant-size memory.
ToRA is a series of Tool-integrated Reasoning LLM Agents designed to solve challenging mathematical reasoning problems by interacting with tools [ICLR'24].
MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversation
Open-source, local-first desktop AI research workbench for scientific computing with Python/R, MCP bioinformatics tools, SSH/WSL/GPU runtimes, and OpenAI/Anthropic models.
Verifiable program-level self-evolution for AI-for-Science agents: Skills and typed Operators grow from replay-verified executions.
The first open-source agentic AI physicist, by Physical Superintelligence PBC (PSI).
Chemcrow
List of Molecular and Material design using Generative AI and Deep Learning
An AI agent system for solving International Mathematical Olympiad (IMO) problems using Google's Gemini, OpenAI, and XAI APIs.
A virtual lab of LLM agents for science research
Robin: A multi-agent system for automating scientific discovery
A next-generation automatic algorithm design platform, making automated algorithm design more accessible and easier to use
ClearAI:以本体为纲的原生 DSH 插件 —— 经证据核验的研究长成可浏览的领域本体。 · ClearAI: an ontology-first DSH agent preset — evidence-checked research that grows into a domain ontology.
🔥🔥🔥 [NeurIPS2025] MM-Agent: LLM as Agents for Real-world Mathematical Modeling Problem
ScienceClaw is a personal research assistant built with LangChain DeepAgents and AIO Sandbox infrastructure, adopting a completely new architecture beyond OpenClaw. It offers stronger security, better transparency, and a more user-friendly experience.
Open-source AI agent for scientific research. Analyze data in Python/R with Claude, GPT, Gemini, and more.
Modular Multi-Agent System for Scientific Research Assistance
Modular Multi-Agent System for Scientific Research Assistance
Design, conduct and analyze results of AI-powered surveys and experiments. Simulate social science and market research with large numbers of AI agents and LLMs.
Orchestrating Mathematical Reasoning Agents with Fact-Graph Memory
Turn any agent into a life science expert with NVIDIA BioNeMo skills.
One open-source modeler for structures, heat and fluids, built from scratch in pure Rust: parametric part in, verified results out. Automatic all-hex and tet meshing, our own nonlinear implicit and explicit FEA, heat transfer and lattice Boltzmann CFD — every result checked against theory. For engineers and AI agents alike. Free, forever.
Local-first, open-source Claude Science alternative, before Claude Science is a thing. Turn your AI agent into personal DNA expert.
Genome viewer for you and your agents.
The Agentic Scientist: Orchestrating Coding Agents for Automated Scientific (Co-)Discovery
The official implementation of "ML-Master: Towards AI-for-AI via Integration of Exploration and Reasoning"
Research Ecosystem for Rigorous and Trustworthy AI Scientists
Code as World: Agentic Discovery of Executable World Representations for Physical Reasoning
BootLoops 1.0: certified computational tools and house engines for exact and high-precision physics and quantitative science, built to be driven by LLM agents. MIT; docs CC BY 4.0.
A customisable 2D platform for agent-based AI research
SciToolAgent: A Knowledge Graph-Driven Scientific Agent for Multi-Tool Integration
Code and data for GeneGPT.
ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents
AI-Powered Bioinformatics Research Assistant. Built on OpenClaw.
Heterogenous Agents Resources & toolKit
An AI research Agent for scientific innovation.
❓Curie: Automated and Rigorous Scientific Experimentation with AI Agents
Composable computational-science methodology skills for AI research agents — pre-registration over TDD. A science-domain reimplementation of Superpowers.
Composable mathematics tools for agents
Foam-Agent: A large language model-based multi-agent framework for automating computational fluid dynamics workflows. Published in Computer Methods in Applied Mechanics and Engineering (CMAME).
A unified framework to solve and analyze heterogeneous-agent macro models.
FOREST is a research agent for long-horizon science, where evidence gets lost, errors compound, and goals drift. It explores ideas, reads literature, forms hypotheses, runs real experiments, analyzes results, revises paths, and builds a full paper—all in an editable graph you can inspect, branch, redirect, with claims and figures linked to evidence
Let AI agents run experiments in any repo while you sleep.
Molecode presents molecules as code and enables LLMs to operate and reason on chemistry directly.
Optimization Modeling Using mip Solvers and large language models
Modex · MH Agent — AI 全自动数学建模智能体,兼顾科研全流程:从赛题到竞赛级论文一夜跑完,国赛/美赛/华为杯全覆盖(架构展示)
An agent-based simulation of corona and other viruses in python
[ICLR 2025 Oral] This is the official repo for the paper "LLM-SR" on Scientific Equation Discovery and Symbolic Regression with Large Language Models
[ICML 2026] Autonomous AI agent for end-to-end spatial proteomics analysis, with SP-Bench for agentic multiplexed-imaging workflows.
Toward Autonomous Scientific Discovery
structural variant calling and genotyping with existing tools, but, smoothly.
Using multi-agent Deep Q Learning with LSTM cells (DRQN) to train multiple users in cognitive radio to learn to share scarce resource (channels) equally without communication
🏭 AI agent platform with skills for protein engineering, the noob-friendly AI tutorial tool for life science professionals. (ACL Demo2025, arXiv 2026)
Molecular dynamics simulations with an LLM agent
An AI Agent for Fully Automated Multi-omic Analyses
EvoMaster: A Foundational Evolving Agent Framework for Agentic Science at Scale.
AI-assisted Lean project automation with DAG blueprints, proof orchestration, and multi-agent coding/proving workflows.
让自动化AI科研只剩最后一块拼图
A curated collection of AI agent skills for biomedical research, covering genomics, proteomics, single-cell analysis, clinical AI, and protein design.
A agent-driven& human-friendly MM-workflow,aiming to autonomously solve math modeling problems and alleviate painful version control issues.
The Station is an open-world multi-agent environment where AI agents pursue autonomous scientific discovery and build a shared literature.
MetaOpenFOAM: an LLM-based multi-agent framework for CFD
AI-driven workbench for computational materials science — interactive 3D structure viewer, natural-language CatBot assistant, visual DAG workflow engine, HPC job submission. Tauri desktop app with SvelteKit frontend and FastAPI Python backend. Drives VASP, ORCA, CP2K, QE, GPAW, DFTB+, SIESTA, LAMMPS.
LLM agents for working with the SRA and associated bioinformatics databases.
Can LLM agents do the work of an operations research practitioner, without an expert reformulating the problem first?
The open-source harness for agentic structural engineering
PowerGridworld provides users with a lightweight, modular, and customizable framework for creating power-systems-focused, multi-agent Gym environments that readily integrate with existing training frameworks for reinforcement learning (RL). https://arxiv.org/abs/2111.05969
CRISPSR-GPT LLM Agent Public Welcome Page
BioAgents: An AI scientist framework for autonomous deep research in biological sciences. Multi-agent system combining literature analysis agents with data scientist agents to enable deep research automation through user feedback integration and iterative scientific discovery. Inspired by advances in Edison Kosmos, Sakana AI, K-Dense and others.
A tool for somatic structural variant calling using long reads
An AI agent for spatial biology
A Large-Scale Knowledge Graph for Automated Scientific Research
Agentic framework for computational chemistry and materials science workflows
pbsv - PacBio structural variant (SV) calling and analysis tools
Ultra-fast methylation calling and event alignment tool for nanopore sequencing data (supports CUDA acceleration)
This repository contains a LLM benchmark for the social deduction game `Resistance Avalon'
Conversational & memory-enabled AI research partner for multi-omics analysis. CLI + Desktop App (installers in Releases). From biological idea to full research paper.
STELLA: Self-Evolving LLM Agent for Biomedical Research
Multi-agent AI system for drug-target identification and due diligence.