Skip to content
TraeIDE

Search

Popular pages

No matching pages

Try a tool name or a topic such as pricing or MCP.

English

Kimi Code CLI Guide

Kimi’s terminal agent for code, shell tasks, skills and parallel subagents.

Last verified: · How we verify
Coding agentMoonshot AImacOSWindowsLinux

Suitable workflows

Repository exploration and coding with Kimi, including migration from the older kimi-cli.

Limitations and billing

The current Node-based release replaces the Python/uv version; migration does not copy login credentials.

Capabilities we verified

Agent workflowCLI surfaceMCPSkillsHooksBring your own keyParallel agents

This is an evidence-based shortlist, not an exhaustive feature inventory. Omitted capabilities have not been checked for this record.

Pricing & usage

See official pricing

Kimi Code account or provider API usage. The cost of metered usage or an external agent can be separate from the subscription.

Check official pricing ↗

Models & access

Kimi Code OAuth, Kimi Platform API keys, or manually configured providers.

Verified families: Kimi.

Official model information ↗

Install and start the CLI

Node.js 22.19+ for npm; Windows also needs Git Bash.

Installation command · npm

npm install -g @moonshot-ai/kimi-code

Open your project folder in a terminal, then run:

kimi
Official installation instructions ↗

Account and authentication

Run /login, then choose Kimi Code OAuth or a Kimi Platform API key.

Project configuration and tools

The new configuration directory is ~/.kimi-code/. After migrating old data, sign in and authorize MCP servers again.

First task to try

Inspect the repository structure, then ask for one small change with its validation steps.

Script usage

This example asks for a project summary. Tool permissions still apply; a prompt is not a sandbox.

kimi -p "Summarize the project structure without modifying files."
Official configuration reference ↗

Related CLI tools

All AI CLI tools →

Project evaluation checklist

  1. Open a small, familiar project and confirm that your essential language tooling works.
  2. Give the agent one bounded change with an observable acceptance criterion.
  3. Review the diff, run the project’s checks and compare the result with your current workflow.
  4. Inspect usage after the task. Estimate a month of similar work, including any separate model or agent bill.