Uncensored modelsfor Hermes Agent
Hermes Agent runs for a long time on its own: it keeps memory, schedules its own work and calls tools without you watching. A refusal three hours into that is a wasted run. Give it a model that does not stop.
Set it up
- Create a key in the dashboard.
- Set the model block in
~/.hermes/config.yamland put the key in~/.hermes/.envas shown. - Or run
hermes model, choose the custom endpoint, and paste the same base URL, key and model id.
~/.hermes/config.yaml and ~/.hermes/.env
# ~/.hermes/config.yaml
model:
provider: custom
base_url: https://uncensoredopencode.com/v1
default: glm-5.3-flash-uncensored
# ~/.hermes/.env
OPENAI_API_KEY=sk-nc-...Good to know
Hermes Agent takes any OpenAI-compatible endpoint as a custom provider, so nothing else needs installing. For an agent that runs unattended, context matters as much as intelligence: every model here holds a million tokens, so a long session keeps its early tool results instead of summarising them away.
GLM 5.3 Flash is a sensible default for the loop. Put Kimi K3.1 Pro behind it for the planning steps if your setup uses more than one model.
Any id on the models page works here, and each is priced by the token.