# IBM/AssetOpsBench

AssetOpsBench - Industry 4.0: A unified benchmark and framework for building, orchestrating, and evaluating domain-specific AI agents for Industry 4.0 asset operations and maintenance, with 460+ scenarios, 5 specialist agents (IoT, FMSR, TSFM, Work Order,...), and multi-agent orchestration blueprints (MetaAgent, AgentHive) over MCP.

Repository: https://github.com/IBM/AssetOpsBench
Canonical: https://ross.abutalabs.com/products/assetopsbench
Language: Python
License: Apache-2.0
License Family: permissive
Topics: llm-agents, model-context-protocol, time-series-forecasting, condition-based-maintenance, hvac-maintenance, iot, predictive-maintenance, ai-for-physical-assets
Last push: 2026-08-26T20:52:33+00:00

## Health v2 (maintenance only)
Score: 64/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 35, longevity 34
- inputs: {"age_days": 489, "days_push": 7, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2237, forks 319 (observed 2026-08-28T04:06:29.477165+00:00)

## What it is
AssetOpsBench is an open-source benchmark and framework from IBM for building, orchestrating, and evaluating domain-specific AI agents for Industry 4.0 asset operations and maintenance. It ships 460+ scenarios across 9 asset classes, five specialist agents (IoT, FMSR, TSFM, Work Order, etc.), and multi-agent orchestration blueprints (MetaAgent, AgentHive) built over the Model Context Protocol.

## Use cases
- benchmark LLM agents on industrial asset maintenance tasks
- build domain-specific AI agents for predictive maintenance
- evaluate multi-agent orchestration for IoT and work order management
- run condition-based maintenance scenarios for HVAC and industrial equipment
- prototype MCP-based agent servers for Industry 4.0 workflows
- compare foundation models on time-series forecasting for asset operations

## When to choose
- you need a standardized benchmark for industrial AI agents
- you are building multi-agent systems over MCP for asset operations
- you want ready-made scenarios and datasets for predictive maintenance research
- you need orchestration blueprints for domain-specific agents

## When to avoid
- you need a production CMMS or EAM system rather than a research benchmark
- your domain is unrelated to industrial asset operations
- you want a no-code agent builder with a polished UI

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, benchmarking, mcp, machine-learning, llm-inference, rag
- domain: artificial-intelligence, iot, large-language-models
- platform: python, windows
- tags: industry-4-0, predictive-maintenance, time-series-forecasting, condition-based-maintenance, multi-agent-orchestration, hvac-maintenance, asset-operations, benchmark-dataset, ai-agents, industrial-automation, linux, macos, docker

## Member repositories
- IBM/AssetOpsBench (main) score 64

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:29.477165+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:44:14.989128+00:00, confidence not recorded.
  - readme: https://github.com/IBM/AssetOpsBench (fetched 2026-08-28T04:06:29.477165+00:00, sha 8907adae35cd)
- Data as of 2026-08-30T08:39:29.467469+00:00.