Science & lab agents
1,137 agents · most starred first
Science & lab agents, page 2 of 12
DiscoveryRSI: Recursively Learning to Discover Valuable Hypotheses
A verification layer for scientific work
[ICLR 2026] Code, benchmark and environment for "ScienceBoard: Evaluating Multimodal Autonomous Agents in Realistic Scientific Workflows"
Medea: An AI agent for therapeutic reasoning across biological contexts
This is the official code of the paper "A Multi-Agent System Enables Versatile Information Extraction from the Chemical Literature"
RS-Agent: An LLM-driven Remote Sensing Intelligent Agent
Multi-agent LLM driven cell type annotation for single-cell RNA-Seq data
[ECCV 2026 🔥] OpenEarthAgent is a unified framework for tool-augmented geospatial agents.
An simple, reliable, and minimal implementation of the AI CoScientist Paper from Google "Towards an AI co-scientist" with Swarms Framework
Python Hydraulic Modeling Tools - 2D
BioDiscoveryAgent is an LLM-based AI agent for closed-loop design of genetic perturbation experiments
[ICML2025 Oral] LLM-SRBench: A New Benchmark for Scientific Equation Discovery with Large Language Models
Circuitron: Agentic PCB Design Accelerator — Generate, plan, and layout circuits from natural language prompts.
A minimalist multi-agent framework for rubost automation of scientific analysis workflows, such as gene expression analysis.
An automatic tool utilizing multi agent framework CrewAI and MCP for VASP calculation.
AI-powered biologics design campaign agent — multi-agent orchestration with BoltzGen, PXDesign, Protenix, and 200+ cloud tools. Antibodies, nanobodies, de novo binders, and beyond.
Variant calling tool for long-read sequencing data
Accurate and flexible loops calling tool for 3D genomic data.
2026 NEO Impact Triage: Bayesian AI Cross-Validation Against Sentry-II & ESA NEOCC
CASSIA: A Multi-Agent LLM-Based Single-Cell Cell Type Annotation Framework
OR-LLM-Agent: Automating Modeling and Solving of Operations Research Optimization Problems with Reasoning LLM
AI Agents for drug discovery, drug development, and other pharmaceutical R&D
LLM Agent for WWTP biotreatment on redefined ASM code library
An agent-based epidemiology simulation framework built in Rust
Auditable AI-assisted scientific research: evidence-gated hypothesis routing, isolated computation, independent replication, and anomaly-sensitive representation repair.
[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: Framework for Vibe Prototyping of AI Agents for Biomedicine
A benchmark suite for evaluating LLM-based interactive scientific reasoning.
Deep active inference agents using Monte-Carlo methods
[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: an open materials-science agent that turns natural-language tasks into reproducible simulation workflows.
Janus: Towards Evolving Agentic Laboratory
ScienceIDE: Turning World’s Scientific Codebase into Agent Learnable Environments
LLM-powered agents for scientific research automation
A collection of agent skills for BioPharma use cases GSDBench Intake https://rconsortium.github.io/pharma-skills/gsdbench-intake/
Autonomous multi-agent system for end-to-end bioinformatics research
longcallR is a tool for SNP calling, haplotype phasing, and allele-specific analysis with long-read RNA-seq data.
An Agentic AI Framework for Ingestion and Standardization of Single-Cell RNA-seq Data Analysis
Agent skills to run computational-chemistry tasks, used in OpenClaw
Closed-Loop Agentic Discovery Engine for Machine Learning Research and Engineering
[NeurIPS 2024] MACM: Utilizing a Multi-Agent System for Condition Mining in Solving Complex Mathematical Problems
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 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!
LLM agent skill files for PyMC and PyTensor
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
Next-gen AI-native tensor-network-based quantum software framework
Harness the scientific methods of Sydney Brenner using AI Agents
AI agents for scientific discovery: papers, tools, and an interactive bilingual atlas with detailed reading guides.
Application of Large Language Models (LLM) for computational materials science - visit jan-janssen.com/LangSim
Paired-scientist AI assistant for reproducible research — lightweight Go runtime, lifecycle hooks, manuscript integration, 12 baseline scientific skills. PicoClaw-compatible.
Code for Temporal Straightening for Latent Planning
A quickstart tool for AmpliconArchitect. Enables all steps (alignment, CNV calling, seed interval detection) prior to running AmpliconArchitect, and invokes AmpliconClassifier
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.
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
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.
[2025 NeurlPS Spotlight] MetaMind: Modeling Human Social Thoughts with Metacognitive Multi-Agent Systems
💊 AI Research Assistant for Accelerated Drug Discovery. 🦞
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.
Modular Agent Based Evolution Framework
transformers safetensors internlm feature-extraction chemistry text-generation
The world’s first science-focused human-AI Agent collaborative discussion community.
Skills & reviewer agents for AI-first climate science — built and used by a PhD atmospheric scientist
COPRA: An in-COntext PRoof Agent which uses LLMs like GPTs to prove theorems in formal languages.
AI Systems as Scientific Instruments for Understanding the Mechanisms of Intelligence
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.
agentic life simulation from inception
API for RL algorithm design & testing of BCA (Building Control Agent) HVAC on EnergyPlus building energy simulator by wrapping their EMS Python API
Autonomous multi-agent framework to optimize scientific software
Code for reproducing the ACL'23 paper: Don't Generate, Discriminate: A Proposal for Grounding Language Models to Real-World Environments
Chemist AI Agent for Developing Materials Datasets with Natural Language Prompts
2024 Alibaba Global Mathematics Competition AI Track Global 2nd Place Project (Agent Universe)
A Formally Grounded, Self-Improving Agentic Framework for Automated Research in Causal Inference
An agentic framework for autonomous protein design
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.
A multi-agent reinforcement learning environment to design and benchmark control strategies aimed at reducing drag in turbulent open channel flow
Circuit design assets, SPICE fixtures, and an auditable Agent workflow
GISclaw: An Open-Source LLM-Powered Agent System for Full-Stack Geospatial Analysis
Open-source quantum Agent workspace with a desktop client, Web UI, messaging, Qiskit/MCP tools, and scientific validation
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.
[ACL 2025] Multi-Agent System for Science of Science
Let AI agents run research experiments + train small language models (in your browser!)
The bioinformatics agent desktop for clinicians and wet-lab scientists — built on DeepSeek Harness. One-click installers, a skill store, offline mode.
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: Framework for Vibe Prototyping of AI Agents for Biomedicine
A Decoupled Architecture for Autonomous High-Energy Physics Phenomenology
STAgent is a multimodal LLM-based AI agent that enables deep research about spatial transcriptomics data
An autonomous photonic device design agent iteratively optimizes silicon photonic devices — no human in the loop.
SpikeAgent is a multimodal LLM-based AI agent that automates and standardizes the spike sorting pipeline
Idea-Catalyst is a metacognition-driven framework for helping humans and LLMs boost their creativity during the scientific brainstorming process.
Reducing Global Carbon Footprint based on Multi-Agent Reinforcement Learning - School of AI Fellowship Research
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 🛫 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 is a framework for agent based modelling in an epidemiological and geographical context.
Agent-based LLM modeling of mechanics problems
Python code to implement LLM4Teach, a policy distillation approach for teaching reinforcement learning agents with Large Language Model
IBL AI Agent helps you use a coding agent such as OpenAI Codex to analyze International Brain Laboratory (IBL) data.
A toolkit for painting agent-based mesoscale molecular simulations and illustrations.
A repository for academic works on RTL generation and Analog circuit generation based on LLM
👩🏻🔬🧪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.
Enhanced and elegant flexible peak/loop/domain -calling and analysis tool for 1D/3D genomic data.