NConnect
DocsKimi K2.7 Code + Unreal Agent

TUTORIAL

How to run Kimi K2.7 Code with Unreal Agent

Run Unreal Labs' async-first Unreal Agent runner on Moonshot AI's Kimi K2.7 Code, served by Nebius Token Factory through NConnect's Responses API proxy.

Kimi K2.7 CodeUnreal Agent 10 minUpdated

Unreal Agent's runner only speaks the OpenAI Responses API, which Nebius does not serve, so NConnect proxies it the same way it proxies Codex. Kimi K2.7 Code is Moonshot AI's code-focused reasoning model for long-context software engineering and tool use, with a 262K-token context window.

Prerequisites

Steps

  1. Install NConnect

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

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

  2. Add your Nebius API key

    nconnect configure

  3. Install Unreal Agent

    Skip this if unreal-agent-runner is already on your PATH. In an interactive terminal, NConnect also offers to run this for you the first time you launch Unreal Agent.

    go install github.com/unreallabsai/unreal-agent/cmd/unreal-agent-runner@latest

  4. Launch Unreal Agent on Kimi K2.7 Code

    nconnect --model moonshotai/Kimi-K2.7-Code unreal

    Everything after unreal goes to the runner, so -p, -workspace and JSON requests work as usual:

    nconnect --model moonshotai/Kimi-K2.7-Code unreal -p "fix the failing test" -workspace .

What NConnect does on launch

  • Registers an Unreal session with the local daemon and points the runner's openai provider at it, entirely through environment variables. There is no config file to write or restore.
  • Gives the runner a per-session daemon token. The Nebius key stays inside the daemon and is removed from the runner's environment.
  • Translates Responses API traffic to Nebius and meters every turn.

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 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 MiniMax M3Pi CodeHow to run MiniMax M3 with Pi CodeRun the Pi coding agent on MiniMax M3, a fast and low-cost reasoning model, served by Nebius Token Factory through NConnect with a temporary provider config. 5 minRead tutorial