On This Page8 sections
Editorial snapshot from September 2026. Prices, models and interface labels may change; this is a practical guide, not a live product feed.
Kimi’s terminal agent for code, shell tasks, skills and parallel subagents.
Coding agent · Moonshot AI · macOS · Windows · Linux
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 workflow · CLI surface · MCP · Skills · Hooks · Bring your own key · Parallel 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.
Models & access
Kimi Code OAuth, Kimi Platform API keys, or manually configured providers.
Verified families: Kimi.
Install and start the CLI
Node.js 22.19+ for npm; Windows also needs Git Bash.
npm install -g @moonshot-ai/kimi-codeOpen your project folder in a terminal, then run:
kimiAccount 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."Related CLI tools
Qwen Code — Qwen’s open-source terminal agent for repository work and configurable model access.
Claude Code — Anthropic’s coding agent for terminal and editor workflows.
CodeBuddy Code — Tencent’s command-line coding agent with regional and enterprise account options.
Project evaluation checklist
- Open a small, familiar project and confirm that your essential language tooling works.
- Give the agent one bounded change with an observable acceptance criterion.
- Review the diff, run the project’s checks and compare the result with your current workflow.
- Inspect usage after the task. Estimate a month of similar work, including any separate model or agent bill.
Related TRAE guides
Continue Reading
More articles connected to the same themes, protocols, and tools.
Referenced Tools
Browse entries that are adjacent to the topics covered in this article.
