Science & lab agents
1,137 agents · most starred first
Science & lab agents, page 3 of 12
An Agent-based Social-ecological System python framework for coupling human-nature researches.
Multi-sport data science Agent Skills library. Portable judgment for sports modeling — doctrine, validation, leakage control, and honest evaluation.
面向 AI/CS 科研的多 Skill 实验智能体:助力全自动科研实验,以 Claim 驱动、骨干实验优先、独立结果审计与 Evidence Freeze,把发散的模型能力收束为可追溯、可复现、可收敛的论文证据。
LLM Agent that leverages cheminformatics tools to provide informed responses.
Code for "Joint Policy Search for Collaborative Multi-agent Incomplete Information Games"
PiFlow: Principle-aware Scientific Discovery with Multi-Agent Collaboration
The self-evolving agentic framework for bioinformatics
Editable ChemDraw (.cdxml/.cdx) figures for Claude Code, Codex & any AI agent: 28 journal & group house styles (JACS, Angew, Nature, Science, Baran, MacMillan), paper & Markush rebuilds (DECIMER OCSR), Excel SAR & substrate tables, stoichiometry calculator, and live ChemDraw OLE in Word & PowerPoint.
An agent that accelerates scientific research by autonomously analyzing provided datasets,great for generating hypotheses, and validating them through code real quick with a single prompt
An End-to-End CFD Agent with Domain-Specific Structured Thinking
Code for the paper "MARL-iDR: Multi-Agent Reinforcement Learning for Incentive-based Residential Demand Response"
Agent-based model of the UK housing market.
[ICLR 2026] SR-Scientist: Scientific Equation Discovery With Agentic AI
CompBioBench: A benchmark of 100 diverse, verifiable questions for agents for computational biology (scripts for running agents)
A Minimal Agent for Automated Theorem Proving
A platform for running AI agents on realtime sport data and make predictions about game outcomes.
EasyGEE agent plugin for Google Earth Engine, geemap, GeoMaster, and local map workflows
Agent Skills for small-molecule and protein therapeutics: cheminformatics, molecular ML, docking and dynamics, protein design platforms, and target-discovery knowledge graphs.
让 Agent 可以直接驱动你的Ansys HFSS 进行天线仿真
AI Agent Skill for scientific data analysis and publication-ready figures in R and Python.
An agentic framework for solving scientific research problems
SMSD Pro: exact substructure, maximum common substructure (MCS) and fingerprint similarity search for chemical graphs in C++, Java and Python, with optional CUDA GPU screening.
This is a reference agent blueprint for AI-powered quantum device calibration. It provides an intelligent agent interface for discovering, executing, and analyzing quantum calibration experiments with support for automated workflows and vision-based analysis.
TADtool is an interactive tool for the identification of meaningful parameters in TAD-calling algorithms for Hi-C data.
Multi agent system for drug discovery tasks
AI Agent leveraging symbolic reasoning and other auxiliary tools to boost its capabilities on various logic and reasoning benchmarks. This project aims to develop a robust and flexible AI system that can tackle complex problems in areas such as decision-making, mathematics, and programming.
[NeurIPS 2025 𝐒𝐩𝐨𝐭𝐥𝐢𝐠𝐡𝐭] AutoToM: Scaling Model-based Mental Inference via Automated Agent Modeling
EarthLink: A Self-Evolving AI Agent System for Climate Science
Vibe Mathematics —— 多代理数学问题求解与形式化验证框架
ChemClaw — The first chemistry-native AI agent skill library.
[NeurIPS 2025] A multi-agent framework that leverages LLMs to simulate socio-economic systems
Plugin for QGIS interaction using LLM. Enables geospatial analysis and data processing through natural language commands.
An AI-native molecular biology workbench for Claude Science: Claude opens sequence files and prepares analyses on request; you annotate, align, and review them in an interactive workspace.
Building a Large Language Model Agent to Become an Expert in the Field of Ceramics.
GATSim: Generative-Agent Transport Simulation
Open-source chemical drawing app for macOS and Windows, with plugins and AI-agent tools (MCP server, CLI, agent skill)
Official implementation of Causal Curiosity: RL Agents Discovering Self-supervised Experiments for Causal Representation Learning at ICML 2021.
llm agent for drug discovery
[ICLR 26] Visual Multi-Agent System: Mitigating Hallucination Snowballing via Visual Flow
Autonomous agents proving theorems in Lean 4 - SETI@Home but for maths proofs using LLMs. Git is the queue, the kernel is the gate, no sorry survives.
Cherimoya is a lightweight sequence-to-function (S2F) model that is small, fast, and easy to use. Now usable by agents.
A land use model based on Cellular Automata and Agent-based modelling.
Recreation of the "Optimal Replacement of GMC Bus Engines" paper by J. Rust, describing a single-agent dynamic optimization model.
BioInformatics Agent (BIA): Unleashing the Power of Large Language Models to Reshape Bioinformatics Workflow
Chemist AI Agent for Rational Inverse Design of Materials
Tools for sgRNA calling in direct capture Perturb-seq data
A framework for discovering, compiling, and validating reusable skills for scientific agents.
Code for AdaJEPA
AI Agentic Research System for Computational Mathematics
AI-powered flood intelligence system featuring h2oGPTe Agent + NVIDIA NIM integration (A2A), NAT pipeline with Nemotron 49B, and real-time flood risk assessment. Part of NVIDIA–H2O.ai AI for Good Blueprint for disaster response and monitoring.
让 Agent 可以直接驱动你的Ansys HFSS 进行天线仿真
[NeurIPS 2026 Oral] DORA: Can LLM Agents Respond to Disasters? Benchmarking Heterogeneous Geospatial Reasoning in Emergency Operations
This repository is an Reinforcement Learning Platform for learning agents to control cyber-physical Power Distribution Systems resiliently. The cyber environment in based on SimPy Discrete Event Simulator, while the distribution system is backened by Open-DSS.
将自然语言描述的 COMSOL 建模需求自动转换为完整 .mph 模型文件的智能 Agent,支持几何、物理场、网格、研究与求解的完整仿真流程。
VALG: An Agentic System for ML Theory Research
[NeurIPS 2025] LabUtopia: High-Fidelity Simulation and Hierarchical Benchmark for Scientific Embodied Agents
AI agents + toolkits for scientific knowledge
docker agent-collab region:us
Conversational agents for engineering simulations with minimal human input using Microsoft AutoGen & GPT-4o.
NeurIPS 2023 paper: De novo Drug Design using Reinforcement Learning with Multiple GPT Agents
AMLP integrates dataset creation, input/output handling, and analysis for machine learning interatomic potentials. It supports Gaussian, VASP, and CP2K, with LLM agents for code selection and ASE-based AMLP-Analysis for molecular simulations and validation.
它是一款面向数学建模的自动化Agent,基于Spring AI Alibaba Graph框架开发:从问题陈述出发自动构建并求解数学模型、进行数据验证与可视化,最终输出包含方法、结果、代码、数据与参考文献的可直接投稿的完整论文。
GIS Agent 是基于 ArcGIS Pro 3.7的 arcpy(支持 GDAL 双后端)的开源地理空间智能体框架:单一有界「观察-决策-执行」循环 + 多角色模型路由,把自然语言指令变成可验收的 GIS 成果——从数据扫描、处理、符号化到地图导出与可编辑 .aprx,配强制验收、配方记忆、断点续跑和本机 Web 控制台。仍在快速迭代,欢迎指出问题
Vision: an economist-directed AI system that takes an economics research question from idea to working paper — identification judgment, adversarial self-refereeing, and total number provenance. Star if you want this to exist; open an issue with the feature you'd want first.
Our math research agent
Framework for scientific llm-based multi-agent systems
The HiPIMS-FLAMEGPU Coupled Model Framework integrates the high-performance hydrodynamic modeling capabilities of HiPIMS with the flexible agent-based modeling environment of FLAMEGPU. This combined framework allows for the simulation of complex interactions between human activities and flooding processes.
Multi-agent LLM driven cell type annotation for single-cell RNA-Seq data
Causal AI Scientist (CAIS) is an LLM-powered tool for generating data-driven answers to natural language causal queries.
Let us make Psychohistory (as in Asimov) a reality, and accessible to everyone. Useful for LLM grounding and games / fiction / business / finance / governance, and can align agents with human too.
Agentic Theorem Prover for Rocq for Program Verification
MolClaw: An Autonomous Agent with Hierarchical Skills for Drug Molecule Evaluation, Screening, and Optimization
CADSmith (formerly AutoFab) is a multi-agent system that generates manufacturing-ready CAD models from natural language by combining LLM code generation with programmatic geometric validation from the OpenCASCADE kernel and visual inspection from an independent vision-language model, iteratively refining until the part is dimensionally correct.
Reinforcement Learning using the Actor-Critic framework for the L2RPN challenge (https://l2rpn.chalearn.org/ & https://competitions.codalab.org/competitions/22845#learn_the_details-overview). The agent trained using this code was one of the winners of the challenge. The code runs on the pypownet environment (https://github.com/MarvinLer/pypownet). It is released under a license of LGPLv3
A platform for Interactive AI-assisted Hypothesis Generation [ACL 2025]
Multimodal-LLM Based AI Agent for Schematic Generation of Analog Circuit
NullFlux:开源的多相流 CFD 智能体工作台(OpenFOAM · MFIX · LBM · DEM)。Apache-2.0
Distributed, objective-led control plane for Lean 4 formalization projects.
A graph-native simulation engine for building composable engineering simulations and digital twins.
Foundation is a flexible, modular, and composable framework to model socio-economic behaviors and dynamics with both agents and governments. This framework can be used in conjunction with reinforcement learning to learn optimal economic policies, as done by the AI Economist (https://www.einstein.ai/the-ai-economist).
Portable MBSE domain agents for AI-assisted systems engineering
Local-first CLI for reproducible biological analysis, with provenance tracked on every step.
The Hierarchical Intrinsically Motivated Agent (HIMA) is an algorithm that is intended to exhibit an adaptive goal-directed behavior using neurophysiological models of the neocortex, basal ganglia, and thalamus.
AI agent for universal behavior analysis (BehaveAgent v1.0).
a peak-calling and differential analysis tool for replicated ChIP-Seq data
GenoTools: Advanced Genotype Data Analysis A robust suite for processing genotype data, offering genotype calling (.idat to PLINK), comprehensive sample/variant QC, and ancestry estimation. Ideal for computational biology and genetics research.
An open-source, AI-driven Social Media Digital Twin powered by LLMs for Computational Social Science simulations, network analysis, and human-agent interaction.
Research Math Agents, Official code release for our paper RMA
Run Claude Science on Windows. A WSL2-backed installer and taskbar launcher for Anthropic's research app.
[KDD 2026] Battery-Sim-Agent: Leveraging LLM-Agent for Inverse Battery Parameter Estimation
Agentic Algorithm Engineering
Agentic framework for scientific research and analysis.
This repository contains the code for the paper "Epidemic modelling with Generative Agents"
BIDARA is a GPT-4o chatbot that was instructed to help scientists and engineers understand, learn from, and emulate the strategies used by living things to create sustainable designs and technologies using the Biomimicry Institute's step-by-step design process.
5th place solution repository for Kaggle CSIRO Image2Biomass, including the experiment workflow used with Claude Code and Codex.
An R package that provides an agent based modeling framework for epidemic models
Edge AI SCADA for hydroponic crop monitoring — Gemma 4 function calling on NFT systems. Kaggle competition entry.
Prover Agent: An Agent-Based Framework for Formal Mathematical Proofs
Neural parameter calibration for multi-agent models. Uses neural networks to estimate marginal densities on parameters and networks