MoonshotAI/kimi-cli

Project overview

Kimi CLI is a terminal-based AI agent that reads and edits code, executes shell commands, searches the web, and plans actions autonomously. The project is gradually being wound down and evolving into Kimi Code CLI, so adoption requires consideration of its lifecycle status.

Project type

MCP · AI Agent · AI Coding

Use cases

Coding & Development · Automation

Deployment

Refer to project documentation

License

Apache-2.0

Best for

• Developers who are comfortable with terminal or CLI tools and need an AI agent to read and edit code, execute shell commands, and search the web from a single interface.

Key capabilities

• Reads and edits code directly to help complete software development tasks.
• Executes shell commands and allows users to switch to shell command mode directly using Ctrl-X.
• Searches and fetches web pages during execution.
• Autonomously plans and adjusts actions during execution.
• Manages Model Context Protocol (MCP) servers via the 'kimi mcp' sub-command group.
• Runs as an ACP agent server to integrate with ACP-compatible editors or IDEs.

Limitations and risks

• Built-in shell commands like 'cd' are not supported in shell mode yet.
• The project is gradually being wound down and is evolving into Kimi Code CLI.

Getting started

• The setup difficulty is rated as easy because the application is installable via pip from PyPI using the command 'pip install kimi-cli'.

Evidence and sources

• README: Kimi CLI is an AI agent that runs in the terminal, helping you complete software development tasks and terminal operations. It can read and edit code, execute shell commands, sear…
• GitHub project description: Kimi Code CLI is your next CLI agent.
• README: This project will be gradually wound down; the docs and existing installations remain available.
• README: You can switch the shell command mode by pressing `Ctrl-X`. In this mode, you can directly run shell commands without leaving Kimi CLI.
• README: Kimi CLI supports MCP (Model Context Protocol) tools.

Reviewed at: 2026-07-18T18:58:39Z