Hermes Agent Integration

Live on the operator's node at ~/.hermes/profiles/frameserv2/ — verified end-to-end ("ARISE" round-trip through hermes → tailnet → llama-swap → MTP inference):

~/.hermes/profiles/frameserv2/config.yaml
---
model:
  default: "qwen38-27b"
  provider: "custom:frameserv2"
  base_url: "http://100.126.153.18:8080/v1"
  api_key: "fs2-"
providers:
  custom:frameserv2:
    base_url: "http://100.126.153.18:8080/v1"
    model_prefix: ""
    api_key: "fs2-"

agent:
  max_turns: 60
  task_completion_guidance: true

display:
  personality: technical
  show_cost: false
  show_reasoning: false
  compact: true

Run it: hermes --profile frameserv2 · one-shot: hermes --profile frameserv2 -z "…"

Switch models by changing model.default to any of the model ids above — one endpoint, three brains:

• qwen38-27b — default. 19.3 t/s served, MTP-accelerated, full vision + tools. Fastest all-rounder.
• flashnext-iq1s — 176B MoE at 31 t/s decode. The heavy hitter.
• glm53-flash — 313B MoE at 14.1 t/s. Deep reasoning (tool calls need a client-side parser until PR-27752 merges its template fix).

Multiple profiles can share this endpoint with different personas (SOUL.md) — same pattern as zaraki/ishigami on ashborn-prime.

from openai import OpenAI
client = OpenAI(base_url="http://frame-serv-2:8080/v1", api_key="not-needed")
r = client.chat.completions.create(
    model="qwen38-27b",
    messages=[{"role": "user", "content": "Hello"}],
)
print(r.choices[0].message.content)

Security posture: no API key — reachability IS the auth, and it's tailnet-scoped. If wider access is ever wanted, add llama-swap API-key middleware first (documented decision point in the change log).

The Model Playground (on the box, tailnet-only) runs one prompt against every model sequentially with live streaming — the fastest way to see the differences.