Research, science & education

Science & lab agents

1,137 agents · most starred first

Science & lab agents, page 5 of 12

scAgent★ 16

scAgent: No-code single-cell analysis for every biologist

marimo-flow★ 16

Agentic scientific-computing platform: a reactive multi-agent team that orchestrates PINA physics-informed neural-network workflows via pydantic-graph, with MLflow tracing/provenance and a marimo chat UI (plus A2A & AG-UI servers).

asb-skill-collections★ 16

Evidence-grounded skills and software-tool records for scientific AI agents, distilled from method papers by the AgenticScienceBuilder pipeline. Skills, Tools, Tasks, Workflows for omics and computationally-accessible sciences.

Analogagent★ 16

Training-free agentic framework for analog circuit design automation: an LLM multi-agent system with self-evolving memory. KDD 2026 (AI4Science, Oral).

compare-bio-llm★ 16

gradio region:us

OpenAIR★ 16

面向科学发现的可信闭环智能体平台 —— 可编排、可验证、可追溯的四阶段科研闭环 | A trustworthy closed-loop agent platform for scientific discovery

mareforma★ 15

Where AI discovery becomes science

Auto-Abaqus-Agent-Research★ 15

AAAR (Auto- Abaqus-Agent-Research)

research-evidence-agent★ 15

Local-first provenance manifests and optional AI audits for research evidence bundles

flare★ 15

Official implementation of "FLARE: Verifying MILP Reformulations with LLM-Based Theorem Proving"

SciPIvot★ 15

SciPIvot: Benchmarking Principal-Investigator Judgment at Pivotal Moments of Scientific AutoResearch Agents

auctopus★ 15

A PI-led laboratory of AI agents for proposing research questions, testing predictions and reviewing results.

labclaw★ 14

Open-source infrastructure for AI-native scientific labs

matmcd★ 14

This is an official repository for "Exploring Multi-Modal Data with Tool-Augmented LLM Agents for Precise Causal Discovery".

pymol-ai-assistant★ 14

A PyMOL plugin that enable ai-assistant. You can use human words to manipulate the molecule.

wheeler★ 14

Turn Claude Code into an interactive scientific workspace: workflow, file system, and knowledge graph.

engineering-run-agent★ 14

Read-only Abaqus, LAMMPS and Slurm run audits with optional OpenAI agent triage

AI4S-Discovery★ 13

多智能体科研助手:文献搜索、知识图谱、TRL评估、创新假设生成

gromacs_smolagent★ 13

An HF's Smolagent to automate molecular dynamics simulations using GROMACS.

biolink-agent★ 13

Multi-agent AI platform for biomedical & genomic research — query PubMed, ClinVar, Ensembl, UniProt and 10+ scientific databases with natural language.

sas2r★ 13

Use R to get R — translate SAS to R with a coordinated multi-agent workflow, built for clinical programming

structure-factory★ 12

AI-agent toolkit for structural biology: design binders, map structures, screen candidates, rank results, and prepare cloud-scale runs.

MechAgent★ 12

自然语言驱动的开源 CAE/FEA 多智能体编排框架

Runtime-AI-Scientist★ 12

Runtime AI Scientist (formerly RAC AI Scientist): official code for "Can AI Scientists Coordinate at Runtime?" (arXiv 2610.00980). Runtime Agent Coordination (RAC) for multi-agent AI scientists such as ARK, Agent Laboratory, and EvoScientist, evaluated on ResearchClawBench.

AgentSense★ 12

LLM agents live out daily routines in simulated smart homes to generate virtual ambient sensor data for activity recognition (AAAI 2026)

starfish-fl★ 11

Starfish-FL is an essential component of the STARFISH project. It focuses on federated learning and analysis for the Analysis Mandate function of STARFISH.

MagLab★ 11

AI for Science harness for magnetism and spintronics research: literature, physics, simulation, fitting, figures, instruments, authoring, and provenance in one CLI.

chemgraph-leaderboard★ 11

gradio leaderboard region:us

abstain-dti★ 11

Calibrated abstention benchmark for drug–target interaction prediction, grounded in physical difficulty coordinates

chelate-shell★ 11

Orchestrating local agent skills into deterministic workflows. Built by @JiamingShi-JsPhys, Chelate Shell enforces a 4-layer routing architecture for research and engineering.

sciclaw★ 10

A paired-scientist agent for reproducible research workflows

opensci-skill★ 10

A Meta-Skill for Building Agent Skills for Scientific Python Libraries

FermiLink★ 10

FermiLink: AI Agent Framework for Multidomain Autonomous Scientific Simulations and Optimization

agentic-reasoning-vpgm★ 10

[AAAI 2026] The official implementation of the paper "BayesAgent: Bayesian Agentic Reasoning Under Uncertainty via Verbalized Probabilistic Graphical Modeling".

automat★ 10

Autoresearch Workflow for Designing Chemical Composition Descriptors

OR-Agent★ 10

Open Research Agent for Operations Research Problems

LLM-Agent-generated-Quadcopter-Prop★ 10

Autonomous multi-agent parametric design + CFD optimization using free local LLMs (Ollama), CadQuery, and OpenFOAM. $0 API cost.

aitomia★ 10

Aitomia: AI agent for computational chemistry

MLR-Copilot★ 10

gradio region:us

Deep-Matter-Chem-Skills★ 10

Reference-audited AI coding-agent skill library for computational chemistry, materials modeling, atomistic simulation, scientific ML, and related workflows.

brain-researcher-public★ 10

Public Brain Researcher code, contracts, docs, and service stack

RF-AIagent★ 10

AI-Agent driven RF design system with HFSS automation for antennas, filters and transmission lines

TCAD-Simulator★ 10

Process-focused TCAD simulator for semiconductor fabrication, featuring voxel-based wafer modeling, lithography and mask workflows, deposition, etch, CMP, implantation, annealing, oxidation, metrology, 3D visualization, WebUI, and recipe design tools.

femis-skill★ 10

Text-portable Agent Skill for FEM/CAE governance: GCI mesh-independence, V&V, execution-mode gates, and headless-vs-human claim discipline across Ansys, Abaqus, Nastran, OpenFOAM, COMSOL and more.

MDArena★ 10

MDArena is an open benchmark for evaluating AI agents on molecular dynamics (MD) workflows.

reason-to-play-src★ 10

Source code for Reason to Play [NeurIPS '26]

DELFIN★ 10

Computational Chemistry Meets Agentic Machine Learning

few-shots★ 10

Open problems in math, science and engineering. One number to beat, one program that checks every answer.

PersonaEvolve★ 9

[EMNLP 2025 Main] Official Repo for Paper: "Implicit Behavioral Alignment of Language Agents in High-Stakes Crowd Simulations"

worldmodel★ 9

The World Model is a framework to train agiens to understand and engineer solutions for the survival machine of life.

BCI-Agent★ 9

AI agent for cell-type specific brain-computer interfaces

Urika★ 9

Multi-agent scientific analysis platform. It creates experiments, tries different methods, evaluates results, searches relevant literature, builds custom tools when needed, and generates detailed reports and presentaions.

SituatedThinker★ 9

[Preprint 2025] SituatedThinker: Grounding LLM Reasoning with Real-World through Situated Thinking

ASTRA★ 9

ASTRA: Automatic Sizing of Transistors with Reasoning Agents

SciConBench★ 9

Official repository for the paper: Can AI Agents Synthesize Scientific Conclusions?

bioengine★ 9

BioEngine is a distributed AI platform that brings the power of cloud computing to bioimage analysis.

chemspacecopilot★ 9
plant-genomics-mcp★ 9

Plant genomics MCP server — 50+ tools across 23 backends (Ensembl Plants, Phytozome, UniProt, AlphaFold DB, PDBe, InterPro, JASPAR, PANTHER, OrthoDB, AraGWAS, NCBI BLAST, Gramene, KEGG, STRING-DB, ATTED-II, BAR, …) + cross-source synthesis. stdio + Streamable-HTTP.

tailaware-rve★ 9

Tail-aware scientific RVE diagnostics with a bounded optional OpenAI agent

plugbo★ 9

A modular framework for agentic Bayesian optimization

KINTSUGI★ 9

Multiplex immunofluorescence image processing pipeline with an optional MCP server for AI assistants

power-electronics-agent★ 9

AI Agent 自动搭建 MATLAB/Simulink 电力电子仿真全通路:五阶段工作流 + ee_lib 物理级模板 + 完整坑地图(从一次真实失败到 500W Boost PFC 验收)

NaN-EcoNet★ 9

🌿 The Agentic Green Ecosystem: Autonomous Waste Logistics (3D-PACO & OR-Tools), Citizen Bulky Recycling (Gemini Vision AI) & Circular 4-Win Economy (EcoPass MCP)

antrikshGPT★ 8

AI-powered space exploration webapp with real-time satellite tracking, astronomical data, and intelligent conversational interfaces for cosmic discovery

AITP-Research-Protocol★ 8

AITP Research Charter and Protocol: a charter-first protocol, contract, and adapter surface for AI-assisted theoretical physics research.

GrasshopperDeepLearningServices★ 8

Deep learning models implemented as web services for integration in Rhino Grasshopper

disaster-manager★ 8

This is the disaster manager created on binary KGEC 2025 this helps users to start ware from any kind of natural disaster through getting informed by nasa satellite data

recursive-consciousness★ 8

Recursive Consciousness: Modeling Minds in Forgetful Systems

audtheia-environmental-monitoring★ 8

AI-powered environmental monitoring system for marine and terrestrial ecosystems using computer vision, real-time analysis, and FAIR data principles.

DeepInflation★ 8

AI Agent for Inflationary Cosmology Research and Model Discovery

ALKYL★ 8

Claude Plugin for CompChem , Drug Discovery & Organic Chemistry reasoning

oih-platform★ 8

OIH: autonomous LLM-agent platform for computational binder design and ADC prioritization

LemmaNet★ 8

Agentic Lemma Discovery for Program Verification in Rocq

dsh-science★ 8

Reproducible Python and R work on DeepSeek Harness, built as plugins.

Folium★ 8

面向控制理论科研的 AI Agent:论文检索 / 理论推导 / 仿真实验闭环,含工具调用、Docker 沙箱、上下文压缩与本地可观测性。

phytonexus★ 8

PhytoNexus is an AI-powered botanical intelligence platform for plant disease diagnosis, multi-agent reasoning, conversational plant care, and comprehensive botanical knowledge.

phytonexus★ 8

PhytoNexus is an AI-powered botanical intelligence platform for plant disease diagnosis, multi-agent reasoning, conversational plant care, and comprehensive botanical knowledge.

genpark-quantum-statevector-simulator-skill★ 8

Universal n-qubit quantum statevector circuit simulator supporting arbitrary unitary gates, Hadamard, CNOT entanglement, Pauli Pauli-X/Y/Z, and multi-qubit measurement with 0-pip pure Python.

genpark-evolutionary-stable-strategy-replicator-dynamics-skill★ 8

Autonomous Agent Evolutionary Stable Strategy (ESS) & Replicator Dynamics Population ODE Solver

genpark-simplex-linear-programming-solver-skill★ 8

Autonomous Agent Two-Phase Simplex Linear Programming Solver with Primal-Dual Tableau & Shadow Price Analysis

genpark-simulated-annealing-combinatorial-optimizer-skill★ 8

Autonomous Agent Simulated Annealing Combinatorial Metaheuristic Optimizer with 2-Opt Neighborhood Perturbation

genpark-shapley-value-cooperative-game-allocator-skill★ 8

GenPark AI Agent Skill - Cooperative game theory Shapley value engine computing fair payoff allocations based on marginal coalition contributions.

genpark-deutsch-jozsa-quantum-oracle-prover-skill★ 8

Deterministic Deutsch-Jozsa quantum algorithm solver distinguishing constant vs balanced Boolean black-box functions in an exact single query with 0-pip Python.

genpark-graham-scan-convex-hull-2d-skill★ 8

Autonomous Agent Monotone Chain Graham Scan 2D Convex Hull with Area & Perimeter Enclosure Calculator

genpark-kalman-filter-1d-state-estimator-skill★ 8

GenPark AI Agent Skill - 1D linear Kalman filter performing optimal state estimation, noisy sensor fusion, and recursive error covariance minimization.

genpark-structural-causal-model-dag-interventional-engine-skill★ 8

GenPark AI Agent Skill - Structural Causal Model (SCM) DAG engine evaluating observational distributions and simulating Pearl's do-calculus interventions.

genpark-propensity-score-inverse-probability-weighting-skill★ 8

GenPark AI Agent Skill - Propensity score matching and Inverse Probability Weighting (IPW) estimator calculating Average Treatment Effect (ATE) under conditional ignorability.

genpark-arithmetic-coding-entropy-compression-skill★ 8

Autonomous Agent 32-bit Finite-Precision Arithmetic Coding Lossless Compression Engine with Underflow Prevention

genpark-branch-and-bound-integer-programming-skill★ 8

Autonomous Agent Branch and Bound Mixed-Integer Linear Programming (MILP) Solver with LP Relaxation Pruning

genpark-singular-value-decomposition-svd-power-iteration-skill★ 8

Autonomous Agent Singular Value Decomposition (SVD) Power Iteration for Low-Rank Dimensionality Reduction

genpark-counterfactual-three-step-abduction-prediction-skill★ 8

GenPark AI Agent Skill - Pearl's 3-step counterfactual inference engine executing Abduction, Action (do-surgery), and Prediction to answer what-if causal inquiries.

genpark-lu-factorization-partial-pivoting-lup-skill★ 8

Autonomous Agent LU Factorization with Partial Pivoting (LUP) Matrix Inversion & Linear Solver

genpark-min-cost-max-flow-successive-shortest-path-skill★ 8

Autonomous Agent Min-Cost Max-Flow (MCMF) Solver via Successive Shortest Path and Residual Network SPFA

genpark-shannon-entropy-mutual-information-estimator-skill★ 8

Autonomous Agent Shannon Entropy, Mutual Information, Kullback-Leibler Divergence & Jensen-Shannon Estimator

klea★ 8

KLEA: Knowledge vaLidated Expert AI assistant for science/research

SciLoom★ 8

SciLoom 科研舱 — AI 辅助的桌面科研管理工作台

labloop★ 8

Agent-driven ML researcher in a secure, reproducible KVM lab: five standalone scientific-state MCP servers within per-user VMs with driver / trusted / hostile zone isolation

verifylab★ 8

A research toolkit for AI agents: tackle hard problems with formal proofs, reproducible checks, and reviews of what was actually proved.

ravel★ 8

Autonomous scientific computing and research system for HEP workflows, from open-physics interpretation to hypothesis generation and iterative experimentation to statistical fits and manuscript drafting.

genpark-ising-model-gibbs-sampler-mrf-skill★ 8

Markov Random Field (MRF) Ising Model Gibbs Sampler simulating ferromagnetic phase transitions, spin couplings, and canonical partition energy distributions.

More in Research, science & education