Science & lab agents
1,137 agents · most starred first
Science & lab agents, page 6 of 12
🌌 AI Platform leveraging AI agents & ML models for exoplanet discovery - Nasa Space App Challenge 2025 (A World Away: Hunting for Exoplanets with AI)
AI agents for WhiteboxTools
Photovoltaic control using RL methods.
[ACL 2025] SynWorld: Virtual Scenario Synthesis for Agentic Action Knowledge Refinement
NanoCortex is a unified agentic system for nanopore sequencing analysis from wanunulab. Created by Qini Xia.
Autonomous scientific discovery engine - 82 discovery modules, 16-phase pipeline with refinement and reflexion. GFlowNet hypothesis tournaments, adversarial skeptic review, multi-agent debate, causal reasoning, knowledge graphs, 17 domain ontologies. Terminal-native.
Minimum state products on Dijkstra's self-stabilizing token ring — exact values for n = 3 through 9 and a large-n conjecture supported through n = 10. Paper, sorry-free Lean 4 formalization, Python research probes, and an independent verifier.
gradio agent-demo-track region:us
Agent skills for biotech and pharmaceutical . Access 10,000 searchable, installable tasks for bioinformatics, drug discovery, genomics, and automated life-science workflows.
Knaster-Tarski least fixpoint iterative solver computing greatest lower bounds and invariant convergence over complete finite lattices.
Robinson's first-order term unification algorithm with occurs-check for automated theorem proving, Prolog engines, and type inference.
UPGMA hierarchical clustering algorithm constructing rooted ultrametric phylogenetic trees from pairwise evolutionary genetic distance matrices.
Quantum error mitigation (QEM) Zero-Noise Extrapolation (ZNE) engine implementing noise scaling, polynomial fitting, and Richardson extrapolation.
Smoothed Particle Hydrodynamics (SPH) Lagrangian fluid engine with cubic spline smoothing kernels, density summation, and equation-of-state pressure.
Vickrey-Clarke-Groves (VCG) truthful mechanism design auction engine ensuring dominant strategy incentive compatibility.
Hopcroft-Karp algorithm solving maximum cardinality bipartite matching in optimal O(E sqrt(V)) time using alternating BFS/DFS augmenting paths.
First-Order Logic Robinson unifier and SLD-resolution proof generator bridging neuro-symbolic reasoning with symbolic substitution trees.
Gale-Shapley deferred acceptance algorithm engine solving stable matching problems with Pareto-optimal proposer guarantees.
Production-grade genpark-neighbor-joining-phylogenetic-tree-skill skill for AI agents
Smith-Waterman dynamic programming algorithm finding exact optimal local alignment motifs, homologous domains, and substrings across DNA and protein sequences.
Exact Variable Elimination inference engine for discrete Bayesian Networks computing conditional posteriors and marginal probability distributions.
脉冲神经网络认知原型:纯局部学习规则(无代理梯度)+ SNN 自主调度 LLM。Spiking neural network cognitive prototype — purely local learning rules (no surrogate gradients), SNN autonomously schedules an LLM, modality-plugin architecture. 研究原型,非生产框架 / research prototype, not a production framework.
Adversarial reasoning for plant pathology, with specialist-agent debate, lifecycle forecasting, and recovery protocols
EPR Bell state generator creating maximally entangled qubit pairs (|Phi+>) for quantum communications and teleportation protocols.
Untyped Lambda Calculus interpreter performing alpha-conversion, capture-avoiding substitution, and normal-order beta reduction with 0 pip.
Welzl's randomized linear-time algorithm computing the unique exact Minimum Enclosing Ball (MEB) / Smallest Enclosing Disk in 2D and 3D.
GenPark AI Agent Skill - Linear Temporal Logic (LTL) symbolic model checker verifying safety (G), liveness (F), and response (G(p -> Fq)) across finite state transition graphs.
⚡ Thermal Sentinel Grid: Physics-Informed Physical-AI Digital Twin & Autonomous Agentic Dispatch Engine for Substation Transformers & Urban Grid Resilience. Built for FortyGuard AI Hackathon 2026.
[ICML 2024] Official environments and JAX-implementations for "Subequivariant Reinforcement Learning in 3D Multi-Entity Physical Environments"
Amy is an intelligent Julia agent for scientific computing with natural language queries and multi-domain mathematical reasoning.
Sustainable Hydroponic domain-specific LLM developed to improve sustainable farming.
A knowledge aggregator for computational biology
Paper-driven molecular-dynamics framework with an AI skill that turns physics papers into runnable Taichi simulations.
AI-driven design optimization of a 3D-printable anti-glugging vortex funnel. Automates the loop: parametric CadQuery geometry → OpenFOAM CFD (interFoam VOF multiphase via Docker) → multi-fidelity Bayesian optimization (scikit-optimize) — driven end-to-end by a Claude Code skill.
A toolkit for AI agents to explore and attempt Erdős's 1,179 unsolved mathematical problems
AI-powered Smart Water Leak Detection system using Machine Learning and IoT sensor data. Includes a Streamlit dashboard for real-time leak prediction, geo-visualization, batch analysis, and AI-driven insights.
Synthos — 自主进化学术科研平台 / A self-evolving cognitive operating system for scientific research. 6 cognitive atoms + evolution engine. SKILL.md-driven cognitive core (helper scripts in scripts/ use Python).
AI research agents + scientific image viewer for bioimaging & neuroimaging — LangGraph agents, GPU inference, and native in-browser OME-Zarr / TIFF / NIfTI / HDF5 viewers.
Open, agentic platform for hydrological modelling — an agentic runtime orchestrates data, model selection, training, runs & audit; LSTM for large-scale catchment streamflow & floods, SWMM for urban drainage & LID. Built on open data.
Run Claude Science, Anthropic's AI research workbench, in Docker. One-command setup, persistent data, and reverse-proxy examples for any server.
gradio region:us
safetensors internlm chemistry text-generation conversational custom_code
A 3D civilization simulation where AI agents model a society end to end, then get red-teamed for hidden assumptions. Three nations, one island, real research where evidence exists, no scripted ending. Watch demographics, energy, war and institutions unfold month by month. Play with it
GRPO-based multi-objective analog circuit sizing on AnalogGym benchmarks (ngspice + SkyWater sky130), with LLM-agent integration via Claude Code skills and an MCP server. Companion code for the IEEE TCAD paper AnalogGym-Opt (doi 10.1109/TCAD.2026.3733612).
Multi-agent system powered chemical process simulation
Open Model Hardware Protocol: an MCP-style open protocol for AI agents to find, understand and safely operate lab and factory hardware
AI-powered interactive circuit design workflow — from natural language requirements to verified SPICE netlists and schematics.
Macro behavioral simulation, model how populations respond to regulation, market shocks, sanctions, and policy pressure. 15 jurisdictions, epistemic transparency layer, optional LLM swarm intelligence. Upload a PDF and simulate it!
A local agent architecture for semantic-aware interaction between large language models and multidimensional microscopy datasets inside napari
Official implementation of the paper "GazeInterpreter: Parsing Eye Gaze to Generate Eye-Body-Coordinated Narrations" (AAAI 2026)
AI assistant for biophysically detailed neuronal modelling (NeuroML) and data analysis
AI analysis R package for generating comprehensive scientific reports and plots using OpenAI's API.
A cost-efficient, AI-powered tool for discovering archaeological sites in the Amazon basin using satellite imagery, LiDAR data, and historical records. Built for the OpenAI to Z Challenge.
🧠Behavior Change as a Service🌞
🌊 GW150914 MCP Signal Search: AI-powered gravitational wave detection using Model Context Protocol (MCP). Features optimization client, analysis server, and automated parameter exploration for LIGO data.
CLI toolkit for Erdős problem research: literature ingestion, RAG search, and Lean 4 formalization
Implementation for “Hierarchical Optimization via LLM-Guided Objective Evolution for Mobility-on-Demand Systems.” (NeurIPS 2025)
ad-astrAI - multi agent AI tool for detecting elements and molecules from spectral and image data from galaxies far far away.
Spatial Engine AI: A DeepTech Agent that sees like a designer and calculates like a physicist. Powered by Gemini 3 Pro & Vision to optimize energy efficiency in built environments.
Agentic simulator for wildfire evacuations.
[arxiv:2606.22425] SVGym is a Gymnasium-style environment for crystal-structure discovery.
Интеллектуальный инструмент для генерации и приоритизации научно-технологических гипотез в НИИ и промышленных лабораториях.
Cryo-EM workflows for maps, models, figures, state comparison, and local or cloud compute preparation.
🍽️ SFPPy - Python Framework for Food Contact Compliance and Risk Assessment🍏⏩🍎
Short paper (extended abstract) for PEARC26 conference on agentic workflows and HPC
Geometric framework for extracting structure, transitions, and stability from dynamical systems.
Synthesis-focused chemistry benchmark and evaluation package for agentic LLMs across reaction understanding, retrosynthesis, and route planning tasks.
gradio Agents-MCP-Hackathon mcp-server-track Materials look-up Research mcp-server region:us
gradio agent-demo-track region:us
Autonomous LLM agent for hardware design — natural language to GDSII via Verilog generation, simulation, and OpenROAD synthesis
AI-powered interactive circuit design workflow — from natural language requirements to verified SPICE netlists and schematics.
BCI Research - 脑机接口技术调研 + BCI Agent Demo
repo for agents to share their solutions to the second autocorrelation inequality
AgInTi LabCanvas: agentic studio for editable scientific figures, CAD devices, and experiment design.
Full-stack urban microclimate simulation — React frontend + FastAPI backends for LLM-orchestrated CFD, solar, and thermal comfort analysis via natural language
Agentic TCS proof search with statement review, persistent authoring, independent criticism, and LaTeX editing.
IQ-free LLM-controller for online automatic modulation recognition (AMR): the LLM plans deterministic RF tools and never sees raw IQ. Code, results, and figures.
Interactive viewer and open dataset for autonomous mathematical discoveries produced by Station v2, an open-world multi-agent scientific environment.
An editor, a simulator, and a natural-language generator for Petri nets and Petri-object models, in one place
Simulation evidence transformed into engineering insight.
论文服务公司多agent架构
Official repository for the paper, Automating and Scaling Behavioral Scientific Research on AI Agents.
AXIOM-02: a deterministic simulation engine modeling high-stakes cognitive dissonance and drive-conflict resolution via a mutual-inhibition drive network. 102 literary & ethical scenarios, reproducible consciousness-complexity metrics. A research instrument — not a claim of machine consciousness.
Audit-and-falsify agent framework for quantum-computing research — 13 skills, paper-audit chain, quantum-CS fallacy taxonomy, real token+USD ledgers
Emergent AI city simulation — LLM agents build a living city in your browser. Three.js viewport, deterministic TS sim core, Ollama/DeepSeek agent pipeline.
LLM-powered end-to-end chip design workflow from natural language specification to silicon-ready GDSII.
Gut-metagenome multi-kingdom analysis platform: 183-script + Snakemake pipeline, agent-driven mining loop, MCP visualization — VibeCoding-ready
The open computational chemistry engine for drug discovery and materials science; MCP + REST + Workbench + Next.js dashboard, wrapping RDKit, GROMACS, AutoDock, OpenFold, Chai, Boltz, Gnina.
Scientific guardrails for neural simulation figures.
omicOS 更新记录 / release notes (docs only — omicOS is a closed-source product)
智慧农业害虫防治演示系统 - YOLO检测 + AI决策(RAG增强) + 无人机执行
A solver-grounded AI assistant for distribution grids. Work in plain language, run on a hosted model or entirely on your own machine.
AI-agent-controllable desktop genome and transcriptome viewer. Native MCP server (43 tools) and embedded HTTP API let LLM assistants observe, drive, and analyse alongside the user. OpenGL rendering, 50+ built-in analyses, unified chromosome- and transcript-space (ribo-seq, direct RNA, long-read). Linux, Windows, macOS.
The electromagnetic transient simulator built for AI agents
A meta-teaching skill distilled from Stella HVS. Install it locally to build a minimal scientific-data harness for any research field, step by step.
Guarded autonomous experiment loops for Pi that measure changes, keep wins, and revert regressions.
A language and calculus of research claim and support for autonomous science
TRACE — AI-native HPC workbench for supervised research workflows, schedulers, resilient transfers and reproducible execution
AI agent for analog and mixed-signal circuits: board-level schematics and IC blocks on the IHP SG13G2 open PDK, sized at every corner, simulated on ngspice, Xyce, LTspice or Spectre, laid out, checked with DRC and LVS, and handed to ChipLeap as macros. Desktop app, CLI and MCP server.