All supported agents
Moonshot AI integration

Run Kimi in Agentastic

Moonshot AI's terminal coding agent, supporting plan mode, unattended work, and directory-aware resume.

kimiChatAuto-approveResumePlan modeInitial prompt

What Agentastic adds

Isolated work

Give every task its own worktree, branch, or container.

Native terminal

Keep Kimi's real CLI and your existing configuration.

Review before merge

Inspect the diff, run code review, test, and open a pull request.

Launch Kimi

  1. Install the official CLI and sign in with your existing provider account.
  2. Open a repository in Agentastic. The connection is discovered from your PATH.
  3. Open Agent Home, choose Kimi, describe the task, and select worktree, local, container, cloud, or remote mode.

Every run gets its own git worktree, so three tasks can share a repository without sharing a branch or a build directory.

What Kimi supports

  • Launch from a task description: supported

    Type the task in Agent Home and Agentastic hands it to kimi at launch, so the run starts from your prompt instead of an empty session.

  • Unattended runs: supported

    Kimi can run without stopping for per-tool confirmation, which is what makes an overnight or scheduled run finish on its own.

  • Plan before editing: supported

    Start Kimi in a read-only pass that proposes an approach without touching the working tree, then approve it and let the same session execute.

  • Resume a session: supported

    Reopen the last Kimi session for a worktree and keep its history — useful when reviewing the diff turns up one more change.

  • Structured chat: supported

    Talk to Kimi in a native chat that renders thinking, nested tool calls, plans, and permission requests as structured events instead of scraped terminal output.

  • Code review: not supported

    Kimi writes the change; pair it with a review-capable agent for the pass before merge.

Agentastic reads these from Kimi's own CLI rather than emulating them, and modes it does not support stay out of the picker. The provider reference lists the exact flags for each launch, and how to compare coding agents covers what changes when you switch harnesses.

Kimi questions

Is there a GUI for Kimi?

Yes. Agentastic runs the real Kimi CLI (kimi) in a native Mac workspace with a git worktree, terminal, diff view, and code review for each task, plus a structured chat view of the session.

How do I run multiple Kimi sessions in parallel?

Start each task from Agent Home in worktree mode. Agentastic gives every run its own git worktree and terminal, so several Kimi sessions can work in one repository without editing the same files.

How do I install Kimi?

Run uv tool install kimi-cli, then sign in the way Kimi's documentation describes. Agentastic finds the kimi command on your PATH when you open a repository.

Does Agentastic charge for Kimi?

No. Agentastic is free and does not proxy model calls. It launches Kimi with the credentials and plan you already use, so any usage is billed by your provider, not by Agentastic.

More supported agents