AssetOpsBench
A unified, open benchmark and framework for building, orchestrating and evaluating domain-specific AI agents for Industry 4.0 asset operations and maintenance, with 140+ scenarios across 9 asset classes and specialist agents for IoT, failure modes and work orders.
AssetOpsBench is a framework for developing, orchestrating and evaluating domain-specific AI agents for industrial asset operations and maintenance, aimed at maintenance engineers, reliability specialists, facility planners and Industry 4.0 researchers. It provides reproducible scenarios, agent tooling and evaluation pipelines for multi-step workflows in simulated industrial environments, combining large language models with time-series foundation models over live sensor data and records such as failure-mode analyses, work orders and alerts.
It covers 9 asset classes and more than 140 scenarios, with domain-specific MCP servers such as an IoT server exposing tools to list sites, assets and sensors and read sensor history, and a failure-mode server that retrieves and generates failure modes, alongside two multi-agent orchestration frameworks and native MCP support.
It installs as an editable Python package from source, and can also be tried without installing anything through a hosted Colab notebook or an interactive Hugging Face playground.