High-accuracy biomolecular structure prediction suite: open-source models (protenix-v2/v1), a benchmark/evaluation toolkit, and a web server for inference. Targets protein/antibody–antigen and ligand-aware predictions with inference-time sampling and constraint support.
Orchestrates sub-agents, persistent memory, and sandboxed execution to run long-horizon LLM workflows and multi-step automation. Ships extensible skills, parallel sub-agents, filesystem sandboxes, and LangChain/LangGraph integration — aimed at research and automation pipelines.
