Hermes Agent

Follow the official installation guide. Run hermes model and choose Custom endpoint, not ChatGPT/Codex Subscription or another provider's OAuth.

Field	Value
Base URL	https://api.nekocloud.vip/v1
API key	Your NekoCloud key
Model	Exact model ID accessible to your group

Save through the wizard and launch hermes. If your version offers transport selection, match Chat Completions, Responses or Anthropic Messages to the model's actual endpoint. Prefer the wizard over replacing config.yaml.

Check HERMES_HOME when using profiles. Auxiliary compression, vision and fallback models may have independent providers; configuring the primary does not configure all of them.

Verification and safety

Back up existing settings and merge only relevant fields; preserve other providers, plugins, MCP and permissions. Protect keys and backups, never commit them. Variables must reach the actual agent process; Remote SSH, containers and desktop processes have separate environments.

Relaunch, select the NekoCloud model, send a short message and match time, model and charge in Usage. Then read a non-sensitive file in an isolated project and verify the tool call, returned result and final answer. Tests can incur charges. Keep approval controls enabled.

This is adapted from official provider configuration guidance, not proof that every model or the complete NekoCloud tool chain has been tested. Check Model Plaza, key groups and troubleshooting.

Official reference

https://hermes-agent.nousresearch.com/docs/integrations/providers