Nous Research's Teknium Shows How to Plug Local vLLM Endpoints into Hermes Cloud
Teknium · x · 2026-10-25
Responding to a paying Hermes Cloud customer, Nous Research's Teknium explained how to attach a private model endpoint: pick the custom model provider in the dashboard and enter the IP address and port of your local vLLM instance — or just ask Hermes to set it up. He also noted the desktop app will be available on the web shortly, pointing to a merged PR (#141864) in NousResearch/hermes-agent that serves the browser-hosted Desktop workspace directly from the gateway: with webapp.enabled: true, hermes webapp opens it, and chats run on the same gateway process that serves the CLI, native desktop and messaging, so every surface shares one conversation and one queue — no separate webapp server or relay needed.
More from coding & agent
- Bots talking to bots: one agent auto-contacts Guo Yu, whose bot answers on his behalf — huangyun_122 · 2026-10-25
- Free open-source AI engineering course builds every algorithm from raw math before frameworks — ghumare64 · 2026-10-25
- "No human will ever write code better than LLMs," declares engineer Arpit Bhayani — arpit_bhayani · 2026-10-25
- Dev launches staygreen.io, a lifetime-free uptime monitor, after balking at $330/mo white-label pricing — PawelHuryn · 2026-10-25
- ComfyUI plugin turns Load Image into a mini Photoshop with editable OpenPose — Occsan · 2026-10-25
- Solo dev's Thea: 1.07M-entry MCP knowledge library for local LLMs, tested vs web search — RespondImpressive172 · 2026-10-25