Kimi Code is Moonshot AI’s terminal coding agent: it reads and edits code, runs shell commands, searches the web, and plans autonomously. The CLI is open source under MIT, and it replaced Moonshot’s original Kimi CLI, archived in September 2026.
models and pricing
Kimi Code defaults to Moonshot’s own models: the K2.7-code family, with K3 and up to 1M context on mid and higher tiers. It is bundled into Kimi memberships from about $19/mo under a rolling 5-hour quota, and API pay-per-token access is available through Moonshot’s platform. The docs say other compatible providers can be configured.
what it’s good at
Kimi Code treats the shell as a first-class surface: a Ctrl-X shell mode lets it work as your shell, not just in it. It ships built-in subagents for coding, exploration, and planning, lifecycle hooks, MCP support with a conversational config flow, editor integration over ACP for Zed and JetBrains, and video input.
Kimi Code in crystl
Kimi Code runs in a crystl shard with its own model selection, activity visibility, and real approval cards for its tool calls. Crystl treats its compatibility as partial because its hook surface can only deny, and because transcript reading and resume by id are both still unwired.
The profile describes what crystl has tested; it never supplies a command, hook script, or launch setting. Those remain local to the Crystl installation.