List Agents
Authorizations
Token-based authentication with required prefix "Token"
Query Parameters
Include archived agents in the response
Filter agents by organization ID
Filter agents by purpose (production, eval, dev)
Filter agents that have ALL of the given tag strings. Repeat the parameter to AND multiple tags, e.g. ?tag=scenario:group-lunch-memory&tag=git-ref:main
Filter agents by template ID
Response
255255255255Custom email alias for the agent's AgentMail inbox (e.g. 'support' becomes support@domain)
255running- Runningsleeping- Sleepingarchived- Archived
running, sleeping, archived 64-2147483648 <= x <= 2147483647Optional cap on how long the agent may sleep, in hours. When set, each harness run is started with --max-utc-sleep = now + this many hours, and sleep requests past that moment are clamped.
0 <= x <= 2147483647Optional git ref (branch/tag/commit) for harness runs. Null = latest main at dispatch time.
255none- Noneminimal- Minimallow- Lowmedium- Mediumhigh- Highxhigh- Extra high
none, minimal, low, medium, high, xhigh Per-agent override for the turn-boundary debounce window (seconds). Leave blank to inherit from the template.
0 <= x <= 2147483647Unused: VAPI calls now use the gpt-realtime-2 model, which only supports a fixed set of OpenAI voices and doesn't support per-agent voice overrides. This field has no effect on call behavior.
255production- Productioneval- Evaldev- Dev
production, eval, dev