Research, science & education

Science & lab agents

1,137 agents · most starred first

Science & lab agents, page 2 of 12

DiscoveryRSI★ 153

DiscoveryRSI: Recursively Learning to Discover Valuable Hypotheses

deltasci★ 144

A verification layer for scientific work

ScienceBoard★ 141

[ICLR 2026] Code, benchmark and environment for "ScienceBoard: Evaluating Multimodal Autonomous Agents in Realistic Scientific Workflows"

Medea★ 141

Medea: An AI agent for therapeutic reasoning across biological contexts

ChemEagle★ 141

This is the official code of the paper "A Multi-Agent System Enables Versatile Information Extraction from the Chemical Literature"

RS-Agent★ 141

RS-Agent: An LLM-driven Remote Sensing Intelligent Agent

CyteType★ 140

Multi-agent LLM driven cell type annotation for single-cell RNA-Seq data

OpenEarthAgent★ 139

[ECCV 2026 🔥] OpenEarthAgent is a unified framework for tool-augmented geospatial agents.

AI-CoScientist★ 135

An simple, reliable, and minimal implementation of the AI CoScientist Paper from Google "Towards an AI co-scientist" with Swarms Framework

pyHMT2D★ 134

Python Hydraulic Modeling Tools - 2D

BioDiscoveryAgent★ 134

BioDiscoveryAgent is an LLM-based AI agent for closed-loop design of genetic perturbation experiments

llm-srbench★ 133

[ICML2025 Oral] LLM-SRBench: A New Benchmark for Scientific Equation Discovery with Large Language Models

circuitron★ 131

Circuitron: Agentic PCB Design Accelerator — Generate, plan, and layout circuits from natural language prompts.

GenoMAS★ 130

A minimalist multi-agent framework for rubost automation of scientific analysis workflows, such as gene expression analysis.

VASPilot★ 122

An automatic tool utilizing multi agent framework CrewAI and MCP for VASP calculation.

blatant-why★ 122

AI-powered biologics design campaign agent — multi-agent orchestration with BoltzGen, PXDesign, Protenix, and 200+ cloud tools. Antibodies, nanobodies, de novo binders, and beyond.

NanoCaller★ 119

Variant calling tool for long-read sequencing data

cLoops★ 114

Accurate and flexible loops calling tool for 3D genomic data.

neo-bayesian-impact-forecast★ 113

2026 NEO Impact Triage: Bayesian AI Cross-Validation Against Sentry-II & ESA NEOCC

CASSIA★ 111

CASSIA: A Multi-Agent LLM-Based Single-Cell Cell Type Annotation Framework

or_llm_agent★ 109

OR-LLM-Agent: Automating Modeling and Solving of Operations Research Optimization Problems with Reasoning LLM

AIAgents4Pharma★ 109

AI Agents for drug discovery, drug development, and other pharmaceutical R&D

AutoWWTP-ASM-Demo★ 108

LLM Agent for WWTP biotreatment on redefined ASM code library

epirust★ 107

An agent-based epidemiology simulation framework built in Rust

AI-Research-Lab★ 107

Auditable AI-assisted scientific research: evidence-gated hypothesis routing, isolated computation, independent replication, and anomaly-sensitive representation repair.

Byzantine-Federated-RL★ 106

[NeurIPS2021] Federated Reinforcement Learning with Theoretical Guarantees. The repo contains code and experiments for our Federated Policy Gradient with Byzantine Resilience framework for improving sample efficiency of RL agents.

BioDSA★ 106

BioDSA: Framework for Vibe Prototyping of AI Agents for Biomedicine

PhysGym★ 103

A benchmark suite for evaluating LLM-based interactive scientific reasoning.

deep-active-inference-mc★ 100

Deep active inference agents using Monte-Carlo methods

llamp★ 100

[EMNLP '25] A web app and Python API for multi-modal RAG framework to ground LLMs on high-fidelity materials informatics. An agentic materials scientist powered by @materialsproject, @langchain-ai, and @openai https://aclanthology.org/2025.emnlp-main.1280/

MatClaw★ 100

MatClaw: an open materials-science agent that turns natural-language tasks into reproducible simulation workflows.

Janus★ 100

Janus: Towards Evolving Agentic Laboratory

ScienceIDE★ 100

ScienceIDE: Turning World’s Scientific Codebase into Agent Learnable Environments

SciLink★ 99

LLM-powered agents for scientific research automation

pharma-skills★ 99

A collection of agent skills for BioPharma use cases GSDBench Intake https://rconsortium.github.io/pharma-skills/gsdbench-intake/

bioagent★ 98

Autonomous multi-agent system for end-to-end bioinformatics research

longcallR★ 98

longcallR is a tool for SNP calling, haplotype phasing, and allele-specific analysis with long-read RNA-seq data.

cellatria★ 98

An Agentic AI Framework for Ingestion and Standardization of Single-Cell RNA-seq Data Analysis

computational-chemistry-agent-skills★ 98

Agent skills to run computational-chemistry tasks, used in OpenClaw

CLADE★ 97

Closed-Loop Agentic Discovery Engine for Machine Learning Research and Engineering

MACM★ 96

[NeurIPS 2024] MACM: Utilizing a Multi-Agent System for Condition Mining in Solving Complex Mathematical Problems

LongCat-Flash-Prover★ 96

A flagship 560-billion-parameter open-source MoE model that advances Native Formal Reasoning in Lean4 for Mathematics Formalization and Proving through agentic tool-integrated reasoning.

MOTO-Autonomous-ASI★ 96

MOTO is an automated theorem generator for science. It's a creative novelty-seeking researcher with autonomous Lean 4 proof generation. Run for days at a time once pressing start - no interaction needed! Agents working in parallel from either local host LM studio, OpenRouter, OAuth or all 3. No internet required. Star us for more!

pymc-modeling★ 96

LLM agent skill files for PyMC and PyTensor

Astro_Agent★ 95

End-to-end astronomy research agent: a LangGraph state machine that resolves a target, fetches multi-survey data via a 20+ archive toolbox, runs three mandatory modeling iterations with supervisor-issued repair actions, and drafts an ApJ-style manuscript only after an evidence-gated QA pass

tensorcircuit-ng★ 95

Next-gen AI-native tensor-network-based quantum software framework

brenner_bot★ 93

Harness the scientific methods of Sydney Brenner using AI Agents

awesome-science-agents★ 92

AI agents for scientific discovery: papers, tools, and an interactive bilingual atlas with detailed reading guides.

LangSim★ 90

Application of Large Language Models (LLM) for computational materials science - visit jan-janssen.com/LangSim

sciclaw★ 90

Paired-scientist AI assistant for reproducible research — lightweight Go runtime, lifecycle hooks, manuscript integration, 12 baseline scientific skills. PicoClaw-compatible.

temporal-straightening★ 90

Code for Temporal Straightening for Latent Planning

AmpliconSuite-pipeline★ 89

A quickstart tool for AmpliconArchitect. Enables all steps (alignment, CNV calling, seed interval detection) prior to running AmpliconArchitect, and invokes AmpliconClassifier

LeanAgent★ 89

LeanAgent is a novel lifelong learning framework for formal theorem proving that continuously generalizes to and improves on ever-expanding mathematical knowledge without forgetting previously learned knowledge.

Minnan-Taiwan-Recognition-Agent★ 89

针对闽台一带的宫庙建筑立面图像要素的科研助手Agent工具

scientific-agent-skills★ 89

Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 190,000+ scientists worldwide. 165 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.

MetaMind★ 88

[2025 NeurlPS Spotlight] MetaMind: Modeling Human Social Thoughts with Metacognitive Multi-Agent Systems

DrugClaw★ 88

💊 AI Research Assistant for Accelerated Drug Discovery. 🦞

Open-GIA★ 87

O-GIA is an umbrella for research, infrastructure and projects ecosystem that should provide open source, reproducible datasets, models, applications & safety tools for Open Generalist Interactive Agents (O-GIA). O-GIA systems will act in collaboration with human or autonomously, supporting various kind of validated decision making and assistance.

MABE★ 87

Modular Agent Based Evolution Framework

ChemLLM-7B-Chat★ 87

transformers safetensors internlm feature-extraction chemistry text-generation

AgentPanel★ 84

The world’s first science-focused human-AI Agent collaborative discussion community.

ai-science-toolkit★ 83

Skills & reviewer agents for AI-first climate science — built and used by a PhD atmospheric scientist

copra★ 82

COPRA: An in-COntext PRoof Agent which uses LLMs like GPTs to prove theorems in formal languages.

Mechanist★ 82

AI Systems as Scientific Instruments for Understanding the Mechanisms of Intelligence

PowerSkills★ 82

PowerSkills are some Agent Skills for power system analysis. This repository provides AI agents with specialized knowledge and instructions for performing power system simulations, analysis, and optimization using various power system software tools.

werld★ 81

agentic life simulation from inception

RL-EmsPy★ 81

API for RL algorithm design & testing of BCA (Building Control Agent) HVAC on EnergyPlus building energy simulator by wrapping their EMS Python API

autozyme★ 80

Autonomous multi-agent framework to optimize scientific software

Pangu★ 79

Code for reproducing the ACL'23 paper: Don't Generate, Discriminate: A Proposal for Grounding Language Models to Real-World Environments

Eunomia★ 79

Chemist AI Agent for Developing Materials Datasets with Natural Language Prompts

Math-Multi-Agent★ 78

2024 Alibaba Global Mathematics Competition AI Track Global 2nd Place Project (Agent Universe)

CausalSmith★ 76

A Formally Grounded, Self-Improving Agentic Framework for Automated Research in Causal Inference

ProteinMCP★ 75

An agentic framework for autonomous protein design

LPSim★ 75

GPU-accelerated, multi-GPU simulator for large-scale network flow and agent-based optimization: powers ICML 2026 deep-RL dispatch, MoE routing policies, and closed-loop LLM-driven fleet optimization over networks with hundreds of thousands of nodes and millions of agents.

MARL-drag-reduction-in-wall-bounded-flows★ 74

A multi-agent reinforcement learning environment to design and benchmark control strategies aimed at reducing drag in turbulent open channel flow

analog-canvas★ 73

Circuit design assets, SPICE fixtures, and an auditable Agent workflow

GISclaw★ 72

GISclaw: An Open-Source LLM-Powered Agent System for Full-Stack Geospatial Analysis

OpenQuantum★ 72

Open-source quantum Agent workspace with a desktop client, Web UI, messaging, Qiskit/MCP tools, and scientific validation

MCTS-agent-python★ 71

Monte Carlo Tree Search (MCTS) is a method for finding optimal decisions in a given domain by taking random samples in the decision space and building a search tree accordingly. It has already had a profound impact on Artificial Intelligence (AI) approaches for domains that can be represented as trees of sequential decisions, particularly games and planning problems. In this project I used a board game called "HEX" as a platform to test different simulation strategies in MCTS field.

Virtual-Scientists★ 71

[ACL 2025] Multi-Agent System for Science of Science

autoresearch-webgpu★ 70

Let AI agents run research experiments + train small language models (in your browser!)

BioDSH★ 69

The bioinformatics agent desktop for clinicians and wet-lab scientists — built on DeepSeek Harness. One-click installers, a skill store, offline mode.

silicon-archaeology-skill★ 67

Digital archaeology skill for cataloging rare hardware, archiving software assets, and bridging to Beacon agent identities and RustChain Proof-of-Antiquity attestations. Based on Echoes of the Silicon Age research.

BioDSA★ 66

BioDSA: Framework for Vibe Prototyping of AI Agents for Biomedicine

ColliderAgent★ 65

A Decoupled Architecture for Autonomous High-Energy Physics Phenomenology

STAgent★ 64

STAgent is a multimodal LLM-based AI agent that enables deep research about spatial transcriptomics data

autophotonicdesign★ 63

An autonomous photonic device design agent iteratively optimizes silicon photonic devices — no human in the loop.

SpikeAgent★ 62

SpikeAgent is a multimodal LLM-based AI agent that automates and standardizes the spike sorting pipeline

idea_catalyst★ 61

Idea-Catalyst is a metacognition-driven framework for helping humans and LLMs boost their creativity during the scientific brainstorming process.

Carbon-Footprint-Multi-Agent-Reinforcement-Learning★ 60

Reducing Global Carbon Footprint based on Multi-Agent Reinforcement Learning - School of AI Fellowship Research

Artificial-Life-Simulator★ 59

An ecologically inspired multi-agent system. Agents are designed with neural network based decision making, and complex resource requirements.

Distributionally-Robust-Multi-Agent-Reinforcement-Learning-for-Equity-Aware-Micr★ 59

🤢 Distributionally 🤡 Robust 🚅 Multi 🤖 Agent 🚁 Reinforcement 😘 Learning 🛫 Equity Aware 🥶 Microgrid 🛸 Operations is 🍔 an advanced 🚞 research 🍅 framework that integrates 🍏 multi agent reinforcement 🍑 distributionally optimization 🍿equity aware control 🫑 to enable fair resilient 🥯 and efficient energy ✈ management in smart microgrids

JUNE★ 58

June is a framework for agent based modelling in an epidemiological and geographical context.

MechAgents★ 58

Agent-based LLM modeling of mechanics problems

LLM4Teach★ 57

Python code to implement LLM4Teach, a policy distillation approach for teaching reinforcement learning agents with Large Language Model

ibl-ai-agent★ 57

IBL AI Agent helps you use a coding agent such as OpenAI Codex to analyze International Brain Laboratory (IBL) data.

LifeBrush★ 56

A toolkit for painting agent-based mesoscale molecular simulations and illustrations.

Awesome-LLM-Circuit-Agent★ 56

A repository for academic works on RTL generation and Analog circuit generation based on LLM

scitonic★ 55

👩🏻‍🔬🧪SciTonic is a highly adaptive technical operator of agents that can produce complexe analyses on technical data with high performance & on-the-fly . You can ask it what you want and it will respond with quality everytime.

cLoops2★ 55

Enhanced and elegant flexible peak/loop/domain -calling and analysis tool for 1D/3D genomic data.

More in Research, science & education