Workbenches
Omni-modal, omni-discipline AI scientist you can run locally across heterogeneous scientific evidence.
Local-first desktop workbench wiring agents, notebooks, runs, figures and review into one auditable provenance trail.
When Agent Becomes the Scientist -- Building Closed-Loop System from Hypothesis to Verification
R&D-Agent: An LLM-Agent Framework Towards Autonomous Data Science
Build Your Personalized Research Group: A Multiagent Framework for Continual and Interactive Science Automation
The Virtual Lab of AI agents designs new SARS-CoV-2 nanobodies
Toward Rigorous and Automated Scientific Experimentation with AI Agents
An AI Agent for Therapeutic Reasoning Across a Universe of Tools
Galaxy for accessible, reproducible, and collaborative data analyses: 2026 update
Plans and implements ML engineering work with arXiv integration and code retrieval.
★ 1.6k
Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models
AI2's science agent family, reproducible and benchmarkable against a rigorous multi-task research suite.
Autonomous deep research over web and local documents with any provider, emitting a cited report.
Long-horizon agent harness that researches, writes code, and produces artifacts.
Fully local, encrypted research agent over arXiv, PubMed, and your own private document collection.
★ 9.1k
Unleashing AI for Accelerated Scientific Research
Hierarchical planner plus specialist agents for deep research and general task execution.
★ 3.5k
Open research assistant combining search, code execution, link resolution and information expansion.
★ 108
LangGraph reference implementation of a deep-research agent, the maintained successor to Open Deep Research.
★ 774
Write Python protocols and execute them on physical Flex and OT-2 liquid-handling robots.
An open-source, hardware-agnostic interface for liquid-handling robots and accessories
Orchestrates beamline and laboratory experiments plus data acquisition, in production at NSLS-II.
a brain for self-driving laboratories
a benchmarking framework for noisy optimization and experiment planning
Build and run a real low-cost autonomous experimentation rig from dimmable LEDs and a spectrophotometer.
165 validated science skills plus database connectors, installable into Claude Code, Cursor or Codex.
Agent skills for topic exploration, literature survey, experiments, paper writing and integrity audit.
★ 215
AI-Driven Exploration in the Space of Code
An Interactive, Extensible, and Controllable Framework for Building Research Agents
Simulator of Human Research Community
Multi-agent simulation of science-of-science dynamics over real publication data.
★ 143
A Scientific Multimodal Foundation Model
Data Formulator 2: Iterative Creation of Data Visualizations, with AI Transforming Data Along the Way
An Information Extraction Toolkit for Chemistry Literature
Robust Molecular Structure Recognition with Image-to-Graph Generation
Data Interpreter: An LLM Agent For Data Science
Communicative Agents for "Mind" Exploration of Large Language Model Society
Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation
Communicative Agents for Software Development
Minimal library for code-writing agents, shipping the reference Open Deep Research implementation.
Gives an agent a real single-GPU nanochat training setup and lets it modify code, train, evaluate, keep or discard.
★ 95k
Markdown-only skill pack for autonomous ML research providing cross-model review loops, idea discovery and experiment automation.
★ 16k
Reimagining Research Papers As Interactive and Reliable AI Agents
Automating Code Generation from Scientific Papers in Machine Learning
Semi-automated research assistant spanning ideation, coding, experiments, writing and publication across Claude Code, Codex, Kimi and OpenCode.
★ 5.4k
An AI Scientist Workspace for Vibe Research
Self-evolving research colleague with 285 skills across 28 disciplines and persistent memory over literature and databases.
A New Framework and Benchmark for Advancing AI Research Agents
AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-bench
DeepReview: Improving LLM-based Paper Review with Human-like Deep Thinking Process
Open Source Planning & Control System with Language Agents for Autonomous Scientific Discovery
Scientific Equation Discovery via Programming with Large Language Models
Evolving scientific discovery by unifying data and background knowledge with AI Hilbert
An LLM Agent for Comprehensive Academic Paper Search
Large Language Models Can Automatically Write Surveys
CLI and leaderboard that autonomously optimizes existing research codebases, publishing results only when an internal ledger confirms improvement.
An Agentic Framework for Computational Chemistry Workflows
Automating Molecular Dynamics Workflows with Large Language Models
Large Language Model Made Powerful for High-fidelity Materials Knowledge Retrieval and Distillation
A Flexible LLM-Based Agent System for Materials Science
An LLM-driven Multi-Agent Framework for Automated Single-cell Data Analysis
An LLM Multi-Agent System for Automated Codification of Research Methodologies
Foundational evolving-agent framework reimplementing the SciMaster line including ML-Master, X-Master and Browse-Master.
★ 220
Skills-only operating layer for LabOS, with no engine of its own.
Nothing matches those filters.