2. What Is KaKeKiKoKu?

KaKeKiKoKu Studio (Knowledge Engine) installs on your computer and accompanies your projects — whether software, writing, research, or anything else — capturing and preserving the knowledge that gets lost between AI work sessions.

The problems it solves

1. Your AI destroys knowledge while working

Every conversation generates decisions, constraints, discarded alternatives, and reasoning. But when the session ends, all of that disappears. The next session starts from scratch: the AI doesn't remember what you decided, what you discarded, or why.

2. Your AI sidesteps problems that aren't its goal

AIs are optimized to solve what you ask them. When they find a secondary problem — a bug, an inconsistency — they mention it in passing and move on. You don't read it because you treat AI output like a compiler: you look at the beginning and the end.

3. You change your project and the knowledge falls behind

The product evolves — be it code, a novel, a thesis — and the documentation rots. With AI it's worse: AI generates changes at a speed no human can document.

4. Your AI answers worse than it could

Without context, your AI guesses. It assumes things about your project, your decisions, your architecture. Sometimes it's right, often it's not. The quality of AI responses is directly tied to how much it knows about your project. Without a system that provides that knowledge, you're paying for a top-tier model that works at half capacity.

How it solves them

KaKeKiKoKu creates structured knowledge files alongside your project files. There are three types:

• File sidecars: accompany a specific file (its code, its document, its image).
• Folder sidecars: describe what a folder contains, its rules, and its purpose.
• Entities: standalone knowledge that doesn't belong to any specific file — architecture decisions, project rules, strategies, concepts.

Each has sections designed to capture the essence of what they document: what it is, what it does, what rules apply, what can go wrong, what was decided, what was discarded and why, what the human intent is. They are not flat documents — they are structured knowledge with purpose.

KaKeKiKoKu maintains an up-to-date index with descriptions of all project resources. When your AI opens the project, it receives this complete index: it knows what everything is without reading it all. If it needs more detail on something specific, it drills down only into that resource. This avoids the "all or nothing" problem of traditional context files, and saves an enormous amount of tokens.

KaKeKiKoKu keeps information always up to date. It monitors your project in real time. When a file changes but its knowledge hasn't been updated, KaKeKiKoKu automatically detects the divergence and alerts your AI to fix the documentation. Without your intervention.

The result: your AI starts every conversation informed, not guessing. It knows your project, your decisions, your constraints. And that translates directly into higher quality responses.

Who is it for

For anyone who works intensively with AI on projects with knowledge worth preserving. You don't need to know how to code. You need a project with files and a frontier model reached through a compatible AI client. I still reach for Claude Opus with Claude Code, but several other models are perfectly capable today — chapter 9 covers what works and why.

Pricing

The core of KaKeKiKoKu — knowledge management, context, synchronization, relationships — is free, with no plans to change this.

For more detail on the history and philosophy behind KaKeKiKoKu, visit kakekikoku.com and the blog.