Files
serverAppConfigs/docs/Dankclaw/Hermes.md
T

2.5 KiB

Hermes

Hermes is the self-improving AI agent from Nous Research. It runs in a terminal, Telegram, Discord, Slack, WhatsApp, or Signal, and keeps a persistent learning loop: it creates skills from experience, searches past conversations, and builds a model of the user across sessions.

Host: Dankclaw — Hostname: hermes.dankclaw.local — Docs: https://hermes-agent.nousresearch.com/docs

Persistent state: /home/dank/hermes-data on Dankclaw, mounted as /data in both containers. The tracked, sanitized configuration baseline is dankclaw/hermes/config.yaml.example.

Facts (from research, primary source)

Item Value
Image built from NousResearch/hermes-agent (official Dockerfile in repo)
License MIT
Model backends Nous Portal, OpenRouter, OpenAI, or any custom endpoint
Interfaces TUI, Telegram, Discord, Slack, WhatsApp, Signal
Memory FTS5 session search, Honcho user modeling
Skills self-created, self-improving during use

Configuration

  • Point Hermes at the local model endpoint or an external provider through its provider config.
  • The gateway process exposes one port for chat integration; the exact port is set in the Hermes config (8090 convention in this repo).
  • The data volume persists skills, memory, and session history.
  • The configured dankserver-small provider reaches http://192.168.0.235:7770/v1 and exposes the frank-default-small alias. It is a named provider, so it can coexist with the existing custom provider for the large model.
  • Both local aliases have agent.reasoning_overrides set to medium. The llama.cpp endpoints reject unsupported values such as high and none; the active large endpoint advertises only low, medium, and xhigh.
  • The live config.yaml contains secrets and user state and is not committed; the tracked example is the sanitized backup of its non-secret settings.

Volumes

Container path Host path (convention)
/data /home/dank/hermes-data

Gotchas

  • Hermes is under active development; pin the image tag for reproducibility.
  • Model choice drives quality; the local frank-default-large (Dankclaw, 7770) is the intended backend.
  • Do not expose the gateway without auth — put it behind Caddy with basic auth.

See Also