Files
obsidian-vault/personal/projects/personal-os/hermes-deployment-patterns.md
T

4.4 KiB
Executable File

title, created, updated, type, namespace, tags, sources, confidence, related
title created updated type namespace tags sources confidence related
Hermes Deployment Patterns 2026-05-29 2026-05-29 concept personal
hermes
architecture
agent
eagle
kraken
infra
medium
tech/hermes-eagle-mac
tech/hermes-docker-kraken
tech/hermes-kraken-api
personal-os-architecture

Hermes Deployment Patterns

Three distinct ways Hermes runs in the Personal OS ecosystem. Each serves a different access model and client type.

Pattern 1: Eagle Native (Mac M4)

Where: Eagle Mac M4 Max, native process (not Docker)
Transport: Zulip (Docker)
Model backend: claude-code-openai-wrapper (Python) on port 8090 — uses claude-agent-sdk to spawn the bundled claude CLI as a subprocess and expose an OpenAI-compatible endpoint with real streaming support.
Previous backend: openclaw-claude-proxy (Node.js) on port 3456 — still running as fallback but streaming broken since CLI ≥ 2.1.141.
Autostart: launchd (com.openclaw.claude-proxy.plist)

Why native: Mac file system access, MCP tools (obsidian-mcp), and the cron wiki-curation job all need full host access. Docker would require volume mounts for every integration.

Key pitfall: claude-python-proxy-start.sh must source ~/.hermes/.env explicitly — launchd does not inherit login session env. Also CLAUDE_CODE_OAUTH_TOKEN expires (access tokens are short-lived); when it does both proxies return 401. See claude-python-cli-proxy for full details and token-refresh procedure.

Pattern 2: Kraken Docker (RPi5)

Where: Kraken RPi5, docker compose из docker/hermes-build/ (⚠️ ранее здесь было «docker run, not compose» — это устарело, проверено 2026-09-23) Transport: Zulip (same instance or separate) Model backend: Gemini or OpenRouter via Hermes gateway Autostart: restart: unless-stopped в compose

Образ: ghcr.io/mallexxx/hermes-kraken:latest (image:, без build:). uid процесса — 1000 (из USER в образе, продублирован в compose как user: "1000:1000"). Config volume: …/docker/hermes/config → /opt/data (HERMES_HOME).

⚠️ Урок (2026-09-23), переносимый на любой Docker-деплой Hermes: uid, под которым стартует контейнер, ОБЯЗАН иметь запись в /etc/passwd. Иначе ssh/git внутри контейнера падают с No user exists for uid <N> до чтения ключа. Записать запись изнутри нельзя (/etc/passwd root-owned) → либо bind-mount готового passwd, либо useradd в Dockerfile, если образ действительно собирается локально. Проверять docker inspect --format '{{.Config.Image}}' + наличие build: в compose до правки Dockerfile. Подробности: tech/hermes-docker-kraken.

See tech/hermes-docker-kraken.

Pattern 3: Kraken API Server (OpenAI-compat)

Where: Kraken RPi5, same hermes-kraken container
Transport: HTTPS via Cloudflare Tunnel (kraken.qentra.top)
Model backend: Gemini / OpenRouter (same gateway)
Clients: Android Aide app (BYOK → Custom Endpoint), any OpenAI SDK

Why Cloudflare Tunnel: no port-forwarding on home router required. The tunnel terminates at cloudflared running with network_mode: host, hitting localhost:8642 directly.

See tech/hermes-kraken-api.

Comparison

Dimension Eagle Native Kraken Docker Kraken API
Model claude-sonnet via Python proxy (8090) Gemini/ORouter Gemini/ORouter
Transport Zulip Zulip HTTPS REST
Clients Cron, MCP tools Zulip bot clients Mobile / OpenAI SDK
External access No No Yes (CF Tunnel)
MCP/tools Full (host access) Docker volumes Not applicable
Rate limits Claude OAuth (proxy workaround) API keys API keys

Design Principle

Hermes deployments follow the client's access model:

  • Interactive/tool-heavy → Eagle native (full host, MCP)
  • Always-on background → Kraken Docker (low-power, 24/7)
  • Mobile / external → Kraken API server (HTTPS, standard protocol)

This avoids running a single large instance with conflicting requirements. See personal-os-architecture for the full system overview.