Kimi Code,
as terminal, thread and conductor.
OpenCognit runs Kimi Code in real terminals or as a thread with approvals — next to Claude Code, Codex, Gemini and Hermes. Kimi can even conduct the others, and its quota is always in view.
Kimi and the others,
in one window.
Kimi Code as you know it,
with a control center around it.
Terminal or thread
Run Kimi in its real terminal — or as a thread: a chat with clear approval cards for every action.
Kimi as the conductor
The orchestrator can run on Kimi: it starts agents, hands out tasks and reports back when they are done.
Quota in view
The card in the sidebar shows your Kimi quota for 5 hours and 7 days — read with your existing login.
Checked before it runs
Kimi starts with a config folder of its own that links to your real one — only the config file gets the check hook. Your ~/.kimi-code stays untouched.
Tasks on the board
Plan a task and start it with Kimi with one click. The card follows the agent: in progress, review, done.
Tokens counted
The Usage page reads Kimi’s local logs and shows tokens and API value per day and project.
Three steps, no new account.
Install Kimi Code
As usual, and log in.
Install OpenCognit
Linux (AppImage, .deb) or Windows. It finds Kimi Code by itself.
Open a project
Start Kimi as a terminal or a thread — or let it conduct.
Questions about Kimi Code
Do I need a Moonshot API key?
No. OpenCognit starts the Kimi Code you already have installed, with your own login.
Does OpenCognit change my Kimi settings?
No. Kimi starts with its own config folder that links to your real one; your configuration stays as it is.
Can Kimi be the orchestrator?
Yes. Claude Code, Kimi Code and Hermes can conduct; you pick the CLI for each new chat.
Does it run on macOS?
Not yet. OpenCognit is available for Linux and Windows.
What does it cost?
Free with up to 4 agents and 2 projects. Pro is a one-time purchase — no subscription on top of your plan.
