← All integrations

Guidewheel

Active

An AI agent for Guidewheel. It works in a scene with a live connection to Guidewheel. It asks before it writes, and every run is traced.

Guidewheel reads the electrical heartbeat of factory machines through clip-on current sensors and derives run/idle/down states, cycles, energy, and operator-tagged downtime issues. Connect a tenant to pin machines and downtime issues as assets, read states, uptime, energy and production actuals — and write back issues, production entries and scrap to close the loop with an ERP or CMMS.

Data & Databases API Key 4 asset types

What you can connect

Add these to your scene and AI gets access.

Guidewheel Account Guidewheel Accounts

A Guidewheel FactoryOps tenant, connected via base URL and API key.

Name
Machine Machines

A sensored machine, line, or cell in Guidewheel.

NameDevice IDStateTarget %
Downtime Issue Downtime Issues

A downtime event or anomaly raised by Guidewheel's alerting.

TitleStatusReasonMachine
Guide Guides

Guidewheel setup guides, troubleshooting, and reference — pin one to read it in-scene, or ask the agent.

TitleSummary

Connect Guidewheel over MCP

Daslab is itself an MCP server.

Connect Guidewheel in a scene, then pin that scene's URL in Claude Code, Cursor, or any MCP client. The agent there gets your Guidewheel tools, and your approval gate and trace travel with them.

https://daslab.run/mcp/<your-world>/<your-scene>

One scene can hold Guidewheel and everything else you connect, so a single endpoint carries them all. Set up a client.

Use cases

  • Pin a machine and read its run/idle/down state over a shift
  • Turn a downtime issue into an ERP/CMMS action and write the reference back
  • Reconcile production actuals, scrap and energy per shift into reports
  • Compute OEE from uptime and production entries — there is no OEE endpoint

Knowledge base

  • Getting Guidewheel API access api-access
    No developer portal — request the tenant base URL, company-scoped API key, and sandbox from Guidewheel; auth, rate limits, and environments.
  • Data model & endpoint map data-model
    Verified against the live API: what the current-sensor signal yields, the two incompatible time conventions, the real paths and field names, and the gaps to plan around.
  • Closing the ERP/CMMS loop erp-cmms-loop
    The two integration patterns — planned orders in / actuals out, and downtime issue to work order with status write-back — as agent flows.

Ships with the integration — agents read these with docs_read, before the account is connected. Knowledge bases →

From Guidewheel

Support: info@guidewheel.com

Ready to try Guidewheel with Daslab?

Get started with CLI