A "Hermes agent" assistant model talks to a Hermes Agent gateway's OpenAI-compatible API server (streamed /v1/chat/completions), with Hermes URL and key settings under Assistant. Hermes keeps the conversation: each assistant session maps to one X-Hermes-Session-Id and only the latest user message is sent. Faceclaw's own tools are not offered to it, and its reasoning stream is not shown on the glasses. See notes/hermes-assistant.md. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
1.6 KiB
Hermes agent as the assistant
The "Hermes agent" assistant model sends what you say to a
Hermes Agent gateway through its
OpenAI-compatible API server and streams the answer back to the glasses. Hermes
runs its own tools and keeps the conversation: each Faceclaw assistant
conversation maps to one Hermes session (X-Hermes-Session-Id), and only the
latest message is sent. Faceclaw's own glasses tools are not offered to Hermes.
Enable the API server in Hermes
In the Hermes config, enable the api_server platform and bind it where the
phone can reach it, then set a key in Hermes's .env and restart the gateway:
hermes config set platforms.api_server.enabled true
hermes config set platforms.api_server.extra.host <address the phone can reach>
hermes config set platforms.api_server.extra.port 8642
echo "API_SERVER_KEY=$(openssl rand -hex 24)" >> ~/.hermes/.env
Check it with curl -H "Authorization: Bearer <key>" http://<host>:8642/v1/models.
Settings (Settings > Assistant)
- Assistant model: Hermes agent. Disabled until the URL is set.
- Hermes URL: e.g.
http://host:8642/v1(a bare host gets/v1added). - Hermes key: the
API_SERVER_KEYvalue.
On iOS, App Transport Security blocks plain http:// to IP addresses unless
App_Resources/iOS/Info.plist has an NSExceptionDomains entry for that host
(NSExceptionAllowsInsecureHTTPLoads); otherwise serve the API over https, for
example with tailscale serve.
Actions that Hermes holds for approval (approvals.mode manual) cannot be
approved from the glasses; approve them from Hermes itself.