Research, science & education

Science & lab agents

1,137 agents · most starred first

Science & lab agents, page 4 of 12

cormas★ 34

CORMAS (COmmon pool Ressources and Multi-Agent Simulations)

agentic-swmm-workflow★ 34

Agentic SWMM is an automated, auditable, and memory-informed framework for reproducible stormwater modelling, integrating QGIS and EPA SWMM through the aiswmm runtime, reusable Skills, and MCP interfaces, with QA verification, provenance tracking, calibration support, and Codex, Hermes, Claude code as well as OpenClaw compatibility

scientific-eval-environments★ 34

Live Knowledge Base of LLM Agents for Science

proxmox-astronomy-lab★ 33

Open-science computational astronomy built to be reproduced. We pursue discovery-oriented research on modern spectroscopic surveys and publish the entire research lab, infrastructure included, as code.

InstructCell★ 33

A Multi-Modal AI Copilot for Single-Cell Analysis with Instruction Following

goose★ 33

Graph Learning for Planning

Sketch2Simulation★ 33

Sketch2Simulation: Automating Flowsheet Generation via Multi Agent Large Language Models

LabOS★ 33

Official Code of LabOS: the AI-XR Co-Scientist that Sees and Works with Humans

CLADD★ 33

The official source code for "RAG-Enhanced Collaborative LLM Agents for Drug Discovery"

yang-mills-mass-gap★ 33

A multi-agent AI framework formalizing the Yang-Mills Mass Gap finite-lattice theory in Lean 4 without axioms or sorry.

MemOmics-Agent★ 33

面向生物信息学的自主科研 Agent:300+ 生信技能、R/Python 持久内核、自主沉淀用户经验、脚本为skill, 审轨+辩论双门控、长任务自愈监督、三层长期记忆;自主构建知识库,查阅、提炼文献,文章思路设计,论文润色,生信分析,可视化,全方位一体。Windows/Linux 开箱即用,接入 DeepSeek/GPT/Claude 等任意 OpenAI 兼容 API 即用。

physics-intern★ 32

Agentic framework for physics

Bis-tools★ 32

A collection of tools to deal with Bisulfite-seq/NOMe-seq (SNP/Methylation calling: BisSNP; HMM segmentation: DMNTools; Visualization/Clustering: alignWigToBed; )

QC3★ 32

QC3, a quality control tool designed for DNA sequencing data for raw data, alignment, and variant calling.

F1-StratLab★ 32

Open-source multi-agent AI platform for Formula 1 race replay, strategy simulation, and explainable race strategy recommendations. (work in progress, MVP in legacy branch)

Alchemi★ 32

Alchemi is a full-stack AI agents for de-novo molecule design, retrosynthetic pathway planning, and molecular simulation, powered by a GATv2 graph neural network, RDKit cheminformatics, and optional LLM reasoning. A Next.js laboratory dashboard sits atop an Express + tRPC orchestration layer bridging a Python FastAPI

LLMTraveler★ 31

LLM-based agent for human travel behavior (day-to-day route choice) simulation.

TrajAgent★ 31

[NeurIPS 2025] TrajAgent: An LLM-Agent Framework for Trajectory Modeling via Large-and-Small Model Collaboration

SeaSID★ 31

Sea safety intelligence dashboard — AI-powered dive condition forecasting for Dauin & Apo Island, Philippines. PyTorch LSTM forecaster with XGBoost baseline and LLM agent, pluggable weather/marine/air-quality providers (Open-Meteo, Storm Glass, AQICN). React 18 + Vite frontend, Python backend, Docker.

vibefeld★ 31

Agent-first CLI tools, UX patterns for LLM agents to prove mathematical results

LLMCWM★ 30

This is the official code repository for the paper "Language Agents Meet Causality -- Bridging LLMs and Causal World Models"

ImplicitAD.jl★ 30

Automates steady and unsteady adjoints (general solvers and ODEs respectively). Forward and reverse mode algorithmic differentiation around implicit functions (not propagating AD through), as well as custom rules to allow for mixed-mode AD or calling external (non-AD compatible) functions within an AD chain.

FEA_Assisted_Agent★ 30

An AI-driven tool integrating Abaqus and OpenAI's LLM for automating finite element simulations, including input file generation, job execution, stress extraction, parametric studies, and sensitivity analysis, streamlining complex workflows for enhanced decision-making.

Mimosa-AI★ 30

Self-evolving AI-Framework for Autonomous Scientific Research (ASR) that writes, runs, and improves its own multi-agent workflows. Powered by MCP tool discovery and Darwinian evolution.

PyLCSS★ 30

Python Low-Code System Solutions

doxa★ 30

Project Doxa is an advanced, autonomous agent-based simulation engine where AI agents act as citizens of evolving civilizations.

open-atp★ 30

OpenATP is an open-source Python package providing a common interface for Automated Theorem Proving (ATP)

SplatLab★ 30

[NeurIPS 2026] SplatLab: Autonomous Scientific Discovery for 3DGS Research. From a one-line idea to reproduced baselines, real GPU experiments, and a compiled paper, driven by Claude Code.

relativitization★ 29

Turn-based strategy game / agent-based simulation framework / social model in 4D relativistic spacetime

MIND★ 29

[ACL 2025] The official pytorch implement of "MIND: A Multi-agent Framework for Zero-shot Harmful Meme Detection".

ChemLLM-7B-Chat-1_5-DPO★ 29

transformers safetensors internlm feature-extraction chemistry text-generation

abaqus_agent★ 29

AI-driven Abaqus workbench: describe a model in a spec, get a real solved one back. Every capability is backed by a check you can run on your own seat, and the gates refuse a doubtful answer instead of returning it. AGPL-3.0 + commercial licence.

EMSeek★ 28

[Science Advances 2026] Bridging Electron Microscopy and Materials Analysis with an Autonomous Agentic Platform

ecology-modeling★ 28

Multi Agent Ecology Modelling

citylearn-2020-pikapika★ 28

CityLearn Challenge Multi-Agent Reinforcement Learning for Intelligent Energy Management, 2020, PikaPika team

Opossum★ 28

Opossum is a tool to pre-process RNA-seq reads prior to variant calling.

synthesis-agent★ 28

2025 LLM Hackathon for Applications in Materials and Chemistry

flowagent★ 28

An advanced multi-agent framework for automating complex bioinformatics workflows.

steer★ 28

STEER — AI4R (AI for Research) experiment framework for auto-research and autonomous research. Connect existing research projects and let an agent edit code and train under governance: frozen task, scorer, and evidence.

Euler★ 28

Mathematical research agents with shared, structured state for understanding the reasoning process and coordinating exploration.

group-social-force★ 27

Multi-Agent Simulation of Collective Behavior (Pedestrian Crowd)

SMIX★ 27

Code for "SMIX(λ): Enhancing Centralized Value Functions for Cooperative Multi-Agent Reinforcement Learning" AAAI 2020

residue★ 27

Hamiltonian decomposition of Z_m^3 Cayley digraphs for all m > 2 — a complete solution to Knuth's "Claude's Cycles," found by LLM agents under a structured exploration prompt. Constructions, proofs, Lean formalization, and a verification suite.

NEURA★ 27

An agentic system for autonomous neuroimaging workflows

DYB-Pro★ 27

DYB Pro hands the protein design pipeline to Devin: state a goal, add sequences, and an autonomous in-silico cycle returns a ranked, order-ready wet-lab shortlist at a fraction of the cost. Devin orchestrates specialist agents whose results commit to a version graph the next cycle reads.

MatAgent★ 27

A physics-aware multi-agent LLM framework for accelerating the material science discovery and optimization

LeanGPT★ 26

Experiments with interactive theorem provers, LLMs and formal systems

agentic-quantum-computing★ 26

End-to-end agentic quantum-ML pipeline: PennyLane GPU quantum-kernel anomaly detection + LangGraph multi-agent system + locally-hosted Qwen3-14B, benchmarked across network-intrusion, LHC physics, and fraud.

proteomics_lab_agent★ 26

A multimodal, agentic AI framework that captures and shares practical expertise by linking written instructions to real-world laboratory work. It uses video analysis to automate documentation and provide personalized guidance, aiming to making complex, hands-on science more accessible and reproducible.

FUSION★ 26

AI research agent for nuclear physics: 23 expert skills that install, run, and verify open-source codes (FRESCO, TALYS, SMASH, ...) plus a 61k-paper offline nucl-th knowledge base

MatSci-LLM-Agents★ 26

Agentic framework combining the power of LLMs with domain-specific tools for materials science, enabling property extraction, simulations, and crystal structure generation to accelerate innovative material design and analysis.

T-REX★ 26

Agentic campaign control for adaptive, multi-method de novo protein binder design under finite compute budgets.

SciExplorer★ 26

Repository for the SciExplorer framework. SciExplorer builds on LLM APIs to create artificial scientist agents that can explore unknown systems by controlling experiments and running analysis code.

GeneX-AI★ 25

A general-purpose computational biology framework integrating LLM multi-agent reasoning with deterministic physical and ecological solvers.

desci-ai-experiments-py★ 25

👾 resources for DeSci + AI experiments: notes, ml, agents, llms, energy based models...

AI4Chem★ 25

AI4Chem is a code to test the ability of large language models (ChatGPT) to comprehend Chemistry.

ai-gene-review★ 25

Demonstration of AI review of existing functional annotations

Vikshep★ 25

Deterministic wavelet-scattering features for physics. Open control plane (AGPL); GPU engine distributed as binaries. Nothing learned, nothing leaked.

rowan-autosearch★ 25

Agent-driven molecular optimization over chemical space, using Rowan for property scoring and RDKit for constraint-aware candidate design.

OpenAaaS★ 25

OpenAaaS: science agent network — bring AI to your data, not your data to AI. AaaS, Agent as a Service, MCP protocol, local execution, Docker sandbox, zero-config Rust nodes.

proteus★ 25

Structural biology superpowers for AI coding agents: PyMOL, ChimeraX, AlphaFold DB, RCSB PDB, UniProt, and Rosetta workflows.

AutoRocq★ 25

Agentic Theorem Prover for Rocq for Program Verification

DrugPilot★ 25

A LLM-based Agent Framework for Drug Discovery

Multimodal-AI-Disaster-Prediction★ 25

🏛 Multimodal 🛖 AI 🏘 Disaster 🏢 Prediction 🏣 is 🏥 an 🏦 advanced ⛪ research 🏩 project 🏪 exploring 🏭 the 🏯 use 🕌 of 🚞 Artificial 🚋 Intelligence 🚌 multimodal ✈ learning 🛸and 🚠 deep 🚟 learning 🚁 to 🛼 improve 🏎 the 🚂 prediction ⚽ early ⚾ detection 🥎 of 🏀 natural 🏐 disasters 🎮

AI-Agents-Autonomous-Scientific-Discovery★ 25

⚽ AI ⚾ Agents 🥎 Autonomous 🏀 Scientific 🏐 Discovery 🏈 is ⛸ an 🎳 advanced 🎮 research 🏆project 🥋 exploring 🎒how 📟 AI ☎ agents 📔 Large 📕 Language 📗 Models📘scientific 📙reasoning 📚 tool 📓 use 📒 autonomous 📃experimentation 💴 can 🧰 transform 🪣 the 🧺 scientific 📁 discovery 🔋 process 📻

Aurora★ 24

Implementation of the paper: "Aurora: A Foundation Model of the Atmosphere" in PyTorch

Flash-P★ 24

Flash-P: Turning decades of biology into accurate causal networks with AI agents

synthetic-gpa-agent★ 24

Synthetic dual-reflection GPA benchmarks with optional OpenAI method-card agent

oh-my-mlip★ 24

Take the pain out of installing and running machine-learning interatomic potentials: every major MLIP in one registry, set up, verified and run by your LLM.

aerospace-team★ 23

12 AI rocket scientists in your terminal. Full satellite mission design from zero to orbit. Production-grade skills with built-in physics, formulas, and validation. No API dependencies.

alphagenome_agent★ 23

static region:us

SciStudio★ 23

AI-native workflow runtime for scientists working with multimodal scientific data.

shannon-prover★ 23

LLM agents that write machine-checked cryptographic proofs in EasyCrypt (arXiv:2607.02847)

stata-ai★ 23

using Stata with AI-Agent

Heinrich-The-Inventing-Machine★ 22

An open-source AI system for TRIZ-based inventive problem solving with interpretable, step-by-step reasoning flow

ZARA★ 22

[ACL 2026] Official implementation of "ZARA: Training-Free Motion Time-Series Reasoning via Evidence-Grounded LLM Agents

DeepWave★ 21

A Deep Learning Approach leveraging Transformer style Architectures for signal classification

gnosislab★ 21

A scientific-method runtime for AI agents: hypotheses, experiments, evidence, provenance, reproducibility, and auditable conclusions.

nopekit★ 21

Explore ideas, engineer real things, and find out what holds up. An AI engineering partner for grounded, evidence-driven design.

PnP-MACE★ 20

Utilities and methods to use the PnP algorithm and MACE framework on image reconstruction problems. Includes demos for superresolution and CT.

deda-drug-evaluation-and-discovery-agent★ 20

An all-in-a-box Drug Discovery AI agent tool

viznoir★ 20

VTK is all you need. AI-Ready VTK visualization for science and engineering.

awesome-ai-scientists★ 20

A curated collection of resources for building “AI Scientist” systems: AI that assists scientific discovery through literature intelligence, hypothesis generation, experiment planning, tool-use, evaluation, and scientific communication. 🌟 Star if you like it!

DFM-Plans★ 20

Discovery Foundation Models (DFMs): From solving tasks to discovering new knowledge.

DrugTargetWorld★ 20

DrugTargetWorld: a synthetic biobank for training and benchmarking AI scientists on end-to-end drug target discovery. Paper: arXiv:2610.09558

route-explainer★ 19

[PAKDD 2024 Oral] Code for "RouteExplainer: An Explanation Framework for Vehicle Routing Problem"

ChatNT★ 19

transformers joblib safetensors ChatNT feature-extraction text-generation

ReAgent★ 19

An AI retrosynthesis framework with multi-objective route scoring, USPTO precedent grounding, and forward-plausibility checks

ltspice-llm★ 19

Run LTspice from Python and from LLMs: headless simulation, .meas results and waveform summaries as JSON, spec checks with guard bands, loop stability margins, KiCad trace parasitics, circuit diff, CSV export, a live run monitor and schematic viewer, OpenAI/Anthropic/Gemini tool schemas, slide and GIF skills. Tested on Windows with LTspice 26.1.1.

GalamseyWatch★ 18

Two-layer agentic Earth Observation on satellite-class compute. Fine-tuned LFM2.5-VL perception + tool-calling agent over Sentinel-2 imagery. Galamsey detection in Ghana as the worked example.

Langtons-Emergence★ 18

Recently I have been researching emergent complexities through first principles reductionism of Langton's Ant and related cellular automata in the hopes that they could potentially offer insights into the emergent intricacies of frontier large language models.

OASiS★ 18

OASiS — an open-source agentic framework for verified multi-physics, multi-code simulation. MCP server letting any AI model drive eight FEM/multiphysics codes (FEniCSx, deal.II, 4C, NGSolve, scikit-fem, Kratos, DUNE-fem, FEBio) plus the SPARTA DSMC particle code, with curated knowledge, verified execution, and cross-code coupling.

crux★ 18

A scientific-method lab notebook your AI agent drives — research as a tree of questions and falsifiable hypotheses in plain markdown, with an LLM literature wiki, a task manager, and a local browser GUI cockpit.

InterpAgent★ 17

Automated Interpretability and Feature Discovery in Language Models with AI Agents

Auto-Abaqus-Agent-Research★ 17

AAAR (Auto- Abaqus-Agent-Research)

satellite-tracker★ 16

WARNING: This repository is no longer maintained ⚠️ This repository will not be updated. The repository will be kept available in read-only mode.

pycantphi★ 16

A Python library to calculate anthropogenic carbon in the ocean.

Langtons-Emergence★ 16

Recently I have been researching emergent complexities through first principles reductionism of Langton's Ant and related cellular automata in the hopes that they could potentially offer insights into the emergent intricacies of frontier large language models.

biocli★ 16

Agent execution layer for biology workflows: batch gene scanning, tumor cohort briefing, target discovery — with structured outputs, resume, and pipeline-ready artifacts

biomed-agent★ 16

Connecting AI to biomedical data

More in Research, science & education