One file. Your AI knows the way.

A common guide for local AI clients

Your AI reads a startup instruction file and uses Studio’s local HTTP connection. The instructions are the same across clients. Only the filename and the place your editor loads it from vary.

You need KaKeKiKoKu Studio 1.17 or later and an AI client already installed. The AI must be able to run local tools that make HTTP requests, such as a terminal. Ordinary browser chat or an agent running on a remote machine cannot reach Studio on your computer through its own localhost.

Start KaKeKiKoKu Studio first, every time. Open it from your applications menu and leave it running while you work. This connection does not start Studio for you.

1. Add the instructions

Save the file where your AI client loads project instructions automatically, usually at the root of the folder you open in that client. If you already have an instruction file, append this section and keep your existing rules. Choose one Wuniq connection method for that workspace so startup rules do not ask for both HTTP and MCP.

• AGENTS.md is the recommended shared file for most clients, including Codex and recent versions of Claude Code, in the terminal or Desktop’s Code tab.
• Already using CLAUDE.md? Keep your instructions. Add the same content there, or keep it in AGENTS.md and import that file with @AGENTS.md from a CLAUDE.md beside it.
• Another client? Use the filename, location, or always-on rule specified in your editor’s documentation. Use the same downloaded content there. A file named AGENTS.md only works if your client actually loads it.

Download AGENTS.md  ·  CLAUDE.md for an existing Claude setup or older version — identical content.

Using Claude? Update your client. Direct AGENTS.md support requires Claude Code 2.1.277 or later. By default, a CLAUDE.md, .claude/CLAUDE.md, or CLAUDE.local.md in your working folder or any parent folder takes precedence. An unconditional .claude/rules/wuniq.md still loads alongside either file. Use one copy of the startup block. See CLI update and loading options or Desktop update and loading options.

Recommended: download the file directly. Save the original file instead of copying its text through a chat or document preview. Some copy-and-paste paths can alter quotes, slashes, or other characters and break the instructions. If you already have an instruction file, merge the downloaded content into it without replacing your existing rules, and check that the URL and quoted JSON examples remain intact.

The downloads use Studio’s default address, http://localhost:5050/api/agent. If you changed the port, replace that address in the file with the one your Studio uses. Keep it local.

# KaKeKiKoKu Studio (local HTTP)

At the start of each conversation, connect to KaKeKiKoKu Studio, the local app that holds
the project knowledge, at `http://localhost:5050/api/agent`:

1. POST `{"action":"initialize","protocolVersion":1}` with
   `Content-Type: application/json; charset=utf-8`.
2. With the returned `sessionId`, send commands as
   `{"action":"run","sessionId":"<sessionId>","command":"<command>"}`.
   Run `open list`, then `help`, and work as `help` explains. Run `help` again if the
   conversation is compacted.

Never pass the JSON as a program argument: it can lose quotes or corrupt non-ASCII text.
In PowerShell use `Invoke-RestMethod`; in other shells pipe it to `curl --data-binary @-`.
If Studio does not answer, ask the human to open it.

This file only starts the connection. Don’t copy your project’s decisions into it, or into your AI’s memory or skills: they live in KaKeKiKoKu. See Avoid competing copies of project knowledge.

No extra CLI, plugin, MCP configuration, or API key is needed for this local connection. Your AI client still uses its own account and normal tool permissions. Studio only accepts connections from this computer and trusts the programs running on it; the session identifier your AI receives is not a password.

2. Start a new conversation and check

Studio shows AI connected once your AI follows the startup instructions and makes its first connection request. Seeing No AI connected beforehand is expected, even if you have already saved the instruction file. Start the conversation and use the prompt below to check the connection.

In Studio, open a project and make it available to AI. Then start a new conversation in the folder containing your instruction file. If your client asks for permission to use a local shell or contact Studio, review and allow the operation through its usual permission controls.

Ask your AI:

Which projects are available in KaKeKiKoKu Studio? Read the context of the project we are working on.

Check the tool activity: the AI should connect locally, run open list, and open and read the relevant project. An empty list means no projects are available to that conversation yet; it is not a connection failure.

Then work normally. The instructions send the AI to help, which tells it to read project context before changes and to run sync afterwards. You can also ask it to sync at any time.

What changes in daily use?

• Open Studio before starting work. Keep it running alongside your editor.
• Use Precise mode in Settings > Application. The AI checks changes through commands; this connection does not receive background MCP channel messages. More about sync.
• Your knowledge stays the same. You can use HTTP and MCP with the same projects. Coordinate edits if several clients work on the same resource.
• A restart is recoverable. If Studio restarts, its replies tell the AI how to reconnect and to check state before repeating a change.

This connection is meant for getting to know KaKeKiKoKu, not for daily work. Your AI writes a shell command for every request, many clients ask you to approve each one, and those extra steps can use somewhat more tokens than MCP. For everyday work and larger projects, we recommend MCP: your AI gets a dedicated tool instead, and your client can start Studio when it needs it. Follow the MCP setup guides, and replace this file’s KaKeKiKoKu block with the MCP one when you switch.

Some AI clients, including coding agents and not only code editors with a built-in assistant, trim long terminal output. For example, in a test with Antigravity 2 (October 2026), a response of about 27,000 characters printed to its terminal arrived with its first lines cut off, while the same response over MCP arrived whole. A long KaKeKiKoKu response can then reach the AI incomplete. If your client does this, or your project is more than a small one, connect through MCP instead.

If it does not connect

• The AI ignores the file: check the required name and location in your client’s documentation, then start a new conversation. Check for conflicting Wuniq startup rules.
• Connection refused: open Studio and check its port. Use a version that includes local HTTP access; an older version may return “not found”.
• The browser can reach Studio but the AI cannot: its shell may run inside WSL, a container, a remote host, or a restricted sandbox. Use an execution environment that can reach the same local Studio instance and review the client’s network permissions. Do not expose Studio to the internet.
• A command failed: ask the AI to read the response and the relevant help topic. The same command help is available through both connections.

The filename is a convention, not a compatibility guarantee. The first-use check above confirms what your client actually does.