Skip to main content
The Agents Catalog is the central place to discover, configure, and deploy agents in Encord — from off-the-shelf integrations to fully Custom Agents.
Custom agents (previously called Editor Agents) enable you to integrate your own API endpoint, such as your own model hosted on a server (or in a cloud function), with Encord to enhance your annotation processes. Any endpoint that accepts a JSON payload can be used to set up a Custom Agent. Agents are triggered while annotating in the Label Editor.

​
Agent Types

In Encord, agents are grouped into:
  • Catalog agents: Built-in agents that you configure with a form (for example, OpenAI or Google Document AI). See Available Agents for a full list.
  • Custom agents, which you configure using the Agents Catalog and trigger from inside the Label Editor. See Custom Agents for details.
  • Task agents, which are Workflow components that automatically operate on all tasks passing through an Agent stage. See Task Agents for details.

​
Enable Agents

  1. Navigate to Agents in the left-hand navigation. The Agents catalog tab opens by default.
  2. Browse or search for agents:
    • Built-in agents are shown as tiles you can configure with API keys and simple options.
    • The Custom agent tile lets you register your own HTTPS endpoint as an agent.
    • A Request agent tile lets you ask Encord to add a new integration.
  3. Click Add to enable an agent. Add external credentials if necessary.
  4. Enabled agents appear in the Enabled tab and can be attached to Projects and used from the Label Editor.

​
External Credentials

Many catalog agents require external credentials, such as OpenAI API keys or Google service accounts. You can add and manage these credentials in two ways:
  • While creating an agent: When you configure a catalog agent, you can choose or create the required external credential directly in the form.
  • From workspace settings: Go to Workspace settings > External credentials to create, reuse, or revoke credentials across agents.
Once configured, credentials can be reused by multiple agents without re-entering secrets.

​
Triggering Agents from the Label Editor

All agents created via the Agents Catalog (built-in and custom) are triggered in the same way from the Label Editor:
  1. Open the data item in the Label Editor.
  2. Right-click in the editor canvas, choose Trigger agent, and select the agent you want to run.