Hermes adds auxiliary model review: /review now spins up sub-agents to audit recent work

Teknium · x · 2026-08-24

Hermes Agent now supports setting an auxiliary model specifically for reviewing work. By running the /review command, the system takes the last 10 messages and the user's prompt, dispatching them to a sub-agent using the specified review model. The sub-agent audits the presented work and sends its critique back to the main agent. This workflow allows users to leverage the blind spots of different models, such as combining Fable with GPT-Sol, for more robust validation.

Related event: Hermes Agent Adds Auxiliary Review Model for /review(4 posts)→

Original post →

More from coding & agent

coding & agent channel →