Control-M for LangGraph

LangGraph enables you to build and run workflows for AI agents with a graph-based structure.

Control-M for LangGraph enables you to do the following:

  • Create a run of an LLM, chain, or Control-M/Agent with specific input and monitor the run execution.

  • Create or redeploy a versioned graph configuration so it runs consistently in the target environment.

  • Manage LangGraph credentials in a secure connection profile.

  • Connect to any LangGraph endpoint.

  • Introduce all Control-M capabilities to Control-M for LangGraph, including advanced scheduling criteria, complex dependencies, resource pools, lock resources, and variables.

  • Integrate LangGraph jobs with other Control-M jobs into a single scheduling environment.

  • Monitor the status, results, and output of LangGraph jobs.

  • Attach an SLA job to the LangGraph jobs.

Setting up Control-M for LangGraph

This procedure describes how to deploy the LangGraph plug-in, create a connection profile, and define a LangGraph job in Control-M SaaS and Automation API.

Before You Begin

Begin

  1. Do one of the following:

    • Install: Run one of the following provision image commands:

      • Linux: ctm provision image LangGraph_plugin.Linux

      • Windows: ctm provision image LangGraph_plugin.Windows

    • Upgrade: Run the following command:

      ctm provision agent::update

  2. Create a LangGraph connection profile in Control-M SaaS or Automation API, as follows:

  3. Define a LangGraph job in Control-M SaaS or Automation API, as follows:

To remove this plug-in from an Agent, see Removing a Plug-in. The plug-in ID is LAN012026.

Change Log

The following table describes changes that were introduced in new versions of this plug-in.

Plug-in Version

Details

1.0.00

Initial version