NVIDIA 开源了这个工具，让 AI 代理能直接调用分子模型做药物发现。用上它任务完成率翻倍还省 Token，做生物计算的同学可以试试。
NVIDIA 开源了 BioNeMo Agent Toolkit，将 OpenFold3、DiffDock 和 GenMol 等生物分子模型包装为 AI 代理可直接调用的技能。每个技能包含模型用途、输入、输出和失败模式说明。在 NVIDIA 使用 Codex CLI 和 GPT-5.5 fast 的基准测试中，该工具将任务完成率从 57.1% 提升至 100%，并实现 token 效率翻倍。
NVIDIA BioNeMo Agent Toolkit Turns Biomolecular Models Into Callable Skills for AI Agents in Drug Discovery
NVIDIA's open-source BioNeMo Agent Toolkit turns biomolecular models like OpenFold3, DiffDock, and GenMol into documented, callable skills for AI agents. Each skill describes a model's purpose, inputs, artifacts, and failure modes, so an agent can select, run, and interpret it. In NVIDIA's benchmarks with Codex CLI and GPT-5.5 fast, skills raised task completion from 57.1% to 100% and doubled token efficiency. The post NVIDIA BioNeMo Agent Toolkit Turns Biomolecular Models Into Callable Skills for AI Agents in Drug Discovery appeared first on MarkTechPost .