Hermes-Local-Ai-Broker-Courses

Lesson 6: Point Claude Code, Cursor, and OpenCode at Your Local AI Broker

2026-10-21 (Modified: 2026-10-21) — Written by SimeonOnSecurity — 8 min read

Configure Claude Code and OpenCode to use one Tailscale Aperture host on your tailnet, and learn why Cursor needs a public endpoint instead.

An illustration of three terminal coding agents connecting to a single private AI gateway host on a dark background with glowing network lines.

#tailscale aperture #hermes agent

Learn more →

Lesson 7: Hermes Bot Profiles: Fan Work Out to Specialized Agents With a Kanban Dispatcher

2026-10-21 (Modified: 2026-10-21) — Written by SimeonOnSecurity — 9 min read

Run one gateway with role-specific Hermes profiles, pin each to a model tier, split a job into dependent kanban cards, and verify every handoff before you trust it.

Diagram of one gateway dispatching work to researcher, writer, and reviewer profiles across linked kanban cards on a dark background

#hermes agent #AI broker #self-hosted ai

Learn more →

Lesson 8: Secure Your AI Broker: Virtual Keys, Budgets, and Allowed Models

2026-10-21 (Modified: 2026-10-21) — Written by SimeonOnSecurity — 10 min read

Give each AI agent its own broker key with rate limits, token and cost budgets, and a fail-closed model allow-list, so one runaway caller stops at its own ceiling.

Diagram of an AI broker checking a virtual key for rate limits, budgets, and an allowed-models list before reaching backends

#AI broker #local ai #self-hosted ai

Learn more →

Lesson 9: Threat Model: Your Local AI Agent Stack Under Attack

2026-10-21 (Modified: 2026-10-21) — Written by SimeonOnSecurity — 10 min read

Map the real attack surface of a local AI agent stack: agents, a Tailscale private edge, an OpenAI-compatible broker, and GPU backends. See which controls hold in code and what stays unsolved.