Agents

DrugAgent is a research multi-agent framework that combines LLM planning with domain-guided code generation to build and evaluate machine-learning workflows for drug discovery.

Molecular Property Prediction · Drug Discovery

STELLA is a research multi-agent framework for biomedical literature and bioinformatics workflows, combining reusable workflow templates, tool orchestration, critique, and optional dynamic tool creation.

Literature & Research · Drug Discovery

ChemAgent (AI4Chem) is a research framework for chemistry and materials tool use, linked to the CheMatAgent paper on tree-search planning, tool execution and ChemToolBench-based training.

Computational Chemistry · Materials Discovery

ChemAgent is a chemical-reasoning research framework that decomposes problems and retrieves reusable memories, with released code for constructing memory pools and running SciBench experiments.

Computational Chemistry

SciAgents is a research multi-agent framework that uses scientific knowledge graphs, LLMs and retrieval tools to develop and critique hypotheses for bio-inspired materials research.

Literature & Research · Materials Discovery

ChatMOF is a code-available research system that uses language-model-guided tools to retrieve MOF data, predict properties and generate structures from natural-language requests.

Materials Discovery

MDCrow is a Python LLM-agent toolset for molecular dynamics workflows, connecting natural-language requests to simulation setup, OpenMM execution, output analysis and scientific information retrieval.

Computational Chemistry

ChemGraph is a Python agent framework that connects natural-language chemistry requests to molecular construction, simulations, analysis, and reporting, with CLI, Python, Streamlit, and MCP interfaces.

Computational Chemistry · Materials Discovery

Coscientist provides a simple implementation and supporting research data for large-language-model chemical research, covering synthesis planning, library selections, repeated runs and optimization.

Literature & Research · Lab Automation

PaperQA provides agentic retrieval-augmented question answering over scientific documents, combining local search, ranked evidence summaries and answers with in-text citations.

Literature & Research

ChemCrow is a Python chemistry agent package built with Langchain that connects language-model reasoning to RDKit, paper-qa, chemical databases, and reaction-planning tools.

Cheminformatics · Literature & Research