API Reference · Activity

The live agent fleet — who is doing what right now

A snapshot of every AI agent in the workspace: each enabled **master** (status, current goal) with its **workers** — every workload carrying an enabled AI daemon plus every browser agent — and, when no master is enabled, the same workers under `standalone`. Worker `activeEdge` marks an in-flight run (a dispatched task or a busy session). The response is cached server-side for a few seconds, so poll freely.

GET/v1/tenants/{name}/agents/fleet

Authorization

x-api-keystringrequired
Your per-workspace API key, e.g. llc_AbC123…. Also accepted as Authorization: Bearer <key>. Mint keys on your workspace's API keys page — each key belongs to one workspace.

Path parameters

namestringrequired
Workspace (tenant) name.

Response

200Masters with their workers, or standalone workers.

mastersarray
standalonearray
The workers when the workspace has no enabled master.
curl https://api.live-llm.com/v1/tenants/acme/agents/fleet \
  -H "x-api-key: $LIVELLM_KEY"
Try itGEThttps://api.live-llm.com/v1/tenants/{name}/agents/fleet
Fill required path param: name.
Example response200
{
  "masters": [
    {
      "id": "master-1",
      "name": "Master 1",
      "provider": "zai-coding-plan",
      "model": "glm-5.2",
      "status": "idle",
      "goal": "",
      "workers": [
        {
          "workloadId": "dev-box",
          "kind": "vm-daemon",
          "status": "working",
          "task": "Refactor the billing tests",
          "activeEdge": true
        }
      ]
    }
  ],
  "standalone": [
    {
      "workloadId": "dev-box",
      "kind": "vm-daemon",
      "status": "working",
      "task": "Refactor the billing tests",
      "activeEdge": true
    }
  ]
}