NConnect
DocsKimi K3 + Hermes Agent

TUTORIAL

How to run Kimi K3 with Hermes Agent

Run Nous Research's Hermes Agent on Moonshot AI's Kimi K3 with a 1M-token context, served by Nebius Token Factory through NConnect. Setup takes about five minutes.

Kimi K3Hermes Agent 5 minUpdated

Hermes Agent from Nous Research is a terminal agent with persistent skills and memory. Kimi K3 is Moonshot AI's frontier open-weights model for coding and agentic tool use, with a 1,048,576-token context window. NConnect connects the two through Nebius Token Factory without touching your Hermes configuration.

Prerequisites

Steps

  1. Install NConnect

    This installs the CLI and the nhermes alias, plus Bun if needed.

    curl -fsSL https://nconnect.sh/install.sh | bash

  2. Add your Nebius API key

    nconnect configure

  3. Install Hermes Agent

    Skip this if hermes is already on your PATH. In an interactive terminal, NConnect also offers to run this for you the first time you launch Hermes Agent.

    curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash

  4. Launch Hermes Agent on Kimi K3

    nconnect --model moonshotai/Kimi-K3 hermes

    Hermes opens with a provider named nconnect and Kimi K3 selected.

What NConnect does on launch

Hermes prefers its own saved credentials over environment variables, so NConnect gives each launch an isolated HERMES_HOME overlay:

  • Sessions, skills, memories and preferences are linked back to your real Hermes home, so they stay native and resumable.
  • Credentials, config and a temporary nconnect provider exist only inside the overlay. Your real Hermes home is never modified.
  • Every Nebius model is registered with the provider, with Kimi K3 first so it becomes the default. You can switch models inside Hermes.

Use the Hermes desktop app

The same launch works for the desktop app:

nconnect --model moonshotai/Kimi-K3 hermes desktop

Track cost and add fallback

Hermes Agent is a spawned harness, so by default it calls Nebius directly and NConnect reports $0.00. Route it through the daemon to meter every turn and get automatic fallback if Kimi K3 is busy:

NCONNECT_METER=1 nconnect --model moonshotai/Kimi-K3 hermes

Then check spend with nconnect usage --last 7d. See Cost metering.

More tutorials

Kimi K3Claude CodeHow to run Kimi K3 with Claude CodeUse Claude Code with Moonshot AI's Kimi K3 and its full 1M-token context, served by Nebius Token Factory through NConnect. No Anthropic account needed. Video included. 5 minRead tutorial Kimi K3Grok BuildHow to run Kimi K3 with Grok BuildUse xAI's Grok Build terminal harness with Moonshot AI's Kimi K3 on Nebius Token Factory. No xAI API key needed, and your Nebius key never reaches api.x.ai. 5 minRead tutorial GLM 5.3Codex CLIHow to run GLM 5.3 with Codex CLIRun OpenAI's Codex CLI on Z.ai's GLM 5.3, a 1M-context model for coding and tool use, served by Nebius Token Factory through NConnect. No OpenAI account needed. 5 minRead tutorial Qwen 3.5 397BOpenCodeHow to run Qwen 3.5 with OpenCodeRun the OpenCode terminal agent on Alibaba's Qwen 3.5 397B, served by Nebius Token Factory through NConnect, without editing your OpenCode config. 5 minRead tutorial