Quick Start
Get KaKeKiKoKu Studio running with your AI in minutes.
What KaKeKiKoKu Studio does
KaKeKiKoKu Studio maintains two layers side by side:
- Your project — the files and results you produce: code, documents, research, anything.
- A knowledge layer — structured context alongside those files: folder sidecars, file sidecars, and standalone entities. Knowledge lives inside the project, not in a separate database.
When your AI opens a project, KaKeKiKoKu hands it a current, summarized tree of all the project's resources — file descriptions, folder rules, entity titles. Your AI is oriented from the first message: no reconnaissance reads, no token waste on rediscovery.
How both layers stay in sync:
- Your AI works on your project as usual.
- KaKeKiKoKu detects when project files change and helps route the knowledge update back through your AI.
- You can see and edit your AI's project knowledge from the KaKeKiKoKu UI at any time. The sidecars and entities are yours to inspect or rewrite.
The result: every session your AI starts with the project's full context — decisions, constraints, rejected alternatives, gotchas — all preserved and current.
Prerequisites
1 KaKeKiKoKu Studio
Go to the Download page and pick the installer for your OS:
Windows
Click Get on the Microsoft Store page. After install, launch KaKeKiKoKu from the Start menu icon, or run wuniq-mcp.exe in a terminal.
Linux
Install it from the Snap Store:
sudo snap install wuniq
For projects in /mnt, /media, USB drives, or VM shared folders, also run sudo snap connect wuniq:removable-media.
KaKeKiKoKu opens its UI at http://localhost:5050 by default. If you see it, you're good.
Recommended: start KaKeKiKoKu before your AI client. Launch it from the Start menu (Windows) or the applications menu (Linux) and it stays up until you exit it, independent of any AI client.
This is the way we recommend using KaKeKiKoKu, for two reasons. It is yours, not your editor's — a knowledge base you can open, read and edit whenever you like, with or without an AI in front of it. And it makes your first message faster: your AI connects to a KaKeKiKoKu that is already running, instead of waiting for one to start.
Letting your AI client start KaKeKiKoKu also works, and there are no duplicates to worry about either way — clients connect to the running KaKeKiKoKu, they never start a second one. But some clients open and close connections while they warm up, so you may see KaKeKiKoKu appear, reconnect and settle. Starting it yourself avoids that entirely.
Working directory
2 Set the working directory
On the welcome screen, set the "Working directory" field — the base folder where you'll organize your projects (e.g. C:\Projects or ~/projects). Everything in KaKeKiKoKu is disabled until a working directory is configured.
Why? AI coding clients usually work from a single folder or workspace. The working directory aligns KaKeKiKoKu with this model: you open your AI client there, and your projects are subdirectories inside it. One directory = one permission boundary = no friction.
Important: Don't create a KaKeKiKoKu project directly at the working directory root. Always use subdirectories (e.g. C:\Projects\MyApp, not C:\Projects). KaKeKiKoKu will prevent this with a clear error message.
Learn KaKeKiKoKu from the inside: right after you set the working directory, KaKeKiKoKu offers to place the
KaKeKiKoKu Studio Learning Lab there — an interactive tutorial that is itself a real KaKeKiKoKu project, in your language, visible to your AI and opened with one click. Ten short stops and a playground with guided exercises cover the first mile; the
user manual covers the depth. You can also open it any time from the
Interactive tutorial link on the welcome screen.
Connect your AI
3 Connect your AI to KaKeKiKoKu Studio
For your AI to work with KaKeKiKoKu Studio, you need two things:
- Point your AI to KaKeKiKoKu Studio — register KaKeKiKoKu as an MCP server in your AI client.
- Add a minimal startup instruction — a small file or rule that tells your AI to use KaKeKiKoKu Studio at the start of every session.
KaKeKiKoKu Studio works with any AI client that supports the Model Context Protocol (MCP). The exact way to do both depends on the client. Open the Integrations matrix to pick the validated client that matches your AI subscription. Each annex covers the full client-specific setup in detail.
KaKeKiKoKu does NOT launch your AI client. You open it however you normally do (terminal, taskbar shortcut, .cmd file you wrote). That simplicity is deliberate — each client has its own way of being launched, and that's not KaKeKiKoKu's job.
Verify
4 Verify the connection
Open a project in KaKeKiKoKu (a subdirectory of your working directory). When your AI uses any KaKeKiKoKu tool, the connection indicator in the KaKeKiKoKu UI turns green.
If your AI client has startup instructions (set up in step 3), your AI will run open list automatically each session. If not, ask it manually: "Run open list with the KaKeKiKoKu tool."
Tip: keep KaKeKiKoKu on screen while you work. KaKeKiKoKu is a local web app, so AI clients with a built-in browser pane can display it right beside the chat — one screen, no window switching, and you get to watch that indicator light up as your AI reads and writes knowledge. Whether your client supports this, and how to set it up, is covered in its
integration annex.
Sync modes: Automatic and Precise
KaKeKiKoKu has two sync modes, toggled from the welcome screen or the bottom status bar (same state, two places to switch it):
- Automatic — KaKeKiKoKu pushes events to the AI in real time (sync requests, drift alerts, "Talk to AI"). Requires a client with channels support. Today, the validated client for this mode is Claude Code with its channels flag. Smoother experience.
- Precise — KaKeKiKoKu detects changes in your project, surfaces them in its UI, and recommends when to sync. When you decide, type sync in your AI chat. Your AI understands the command and works with KaKeKiKoKu until the knowledge layer is up to date. Works with any MCP client.
Precise mode may sound more manual, but in practice it feels natural with strong coding models. Assistants such as Codex often remember to synchronize as part of their normal workflow, and KaKeKiKoKu's clipboard flow for "Talk to AI" prompts keeps the interaction smooth. If you want to force a synchronization at any point, type sync in the AI chat. Automatic is more seamless when channels are available; Precise is not a second-class mode.
Default for new installs: Precise. Switch to Automatic only if your client supports channels and you launched it with the appropriate flag — KaKeKiKoKu shows a confirmation dialog the first time.
You're not just a spectator. KaKeKiKoKu includes an editor. You can — and should — open any sidecar or entity and edit knowledge directly: refine wording, add rules, capture decisions, fix what your AI missed. This works in both modes.