Webhooks
A webhook lets almyty notify your systems when an agent finishes a run. Give an agent a webhook URL and almyty sends it a POST with the execution result (status, output, cost, and tokens), so downstream systems can react without polling.

Set it up
On the agent’s detail page, turn on the webhook, paste the URL almyty should call, and save. From then on, every completed run POSTs to that URL.
The request is hardened: the target URL is validated against SSRF (no internal or link-local hosts), redirects are not followed, and the call times out quickly. A failed webhook is logged but never fails the run.
What you receive
almyty POSTs this JSON when a run completes:
{
"event": "agent.execution.completed",
"timestamp": "2026-06-30T09:08:00.000Z",
"agent": { "id": "<agent-id>", "name": "Customer Support Orchestrator" },
"execution": {
"id": "<execution-id>",
"status": "completed",
"output": { "...": "the agent's result (truncated if very large)" },
"executionTime": 17700,
"totalCost": 0.0581,
"totalTokens": 2364,
"error": null
}
}Triggering an agent
A webhook is for outbound notifications, not for starting a run. To invoke an agent from an external system, call the OpenAI-compatible API or the agent’s invoke endpoint, or run it on a schedule.
Related
- Scheduling: run an agent on a recurring interval
- OpenAI-compatible API: invoke an agent