brain:init

Initialize a persistent project brain database from existing repository knowledge.

264|11|Updated Apr 25, 2026

Search Tags:#documentation #sqlite #deduplication #bootstrap #knowledge-base #brain #project-scanning

Ready to run

npx skills add https://github.com/coco-research/coco --skill brain-init-coco-research

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: brain:init
Source: https://github.com/coco-research/coco/tree/main/systems/brain/skills/brain-init
Command: npx skills add https://github.com/coco-research/coco --skill brain-init-coco-research

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It bootstraps a persistent project brain so an AI assistant can capture, update, and reuse repository knowledge without re-reading everything from scratch.

Core Features & Use Cases

Initializes a project_brain.db in the current folder and creates the first project record.
Scans knowledge sources such as CLAUDE.local.md, CLAUDE.md, memory files, docs, emails, and reference documents to build an indexed knowledge base.
Handles re-runs safely by skipping existing entries, processing only new or changed files, and updating the manifest after writes.
Use it when you want to onboard a codebase, maintain a living project memory, or generate downstream knowledge articles from captured evidence.

Quick Start

Ask the brain:init skill to initialize the current project folder from existing CLAUDE files, docs, emails, and memory notes.

Frequently Asked Questions about brain:init

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I bootstrap a persistent knowledge base from existing project documentation?▼

The project brain uses a SQLite database to store indexed knowledge from scanned documentation, memory files, and emails. It ensures idempotent scans and deduplicates entities and decisions, so re-running the initialization safely skips existing entries and only processes new or changed files.

How do I initialize a project brain database from CLAUDE.md and memory files?▼

You initialize the project brain by running the skill in your project folder, which triggers an automated scan of CLAUDE.md, memory files, and reference documents to populate the SQLite database and update the knowledge manifest incrementally.

Can I use this to onboard a codebase by scanning reference documents and emails?▼

Yes, you can onboard a codebase by scanning reference documents and emails. The initialization process captures knowledge incrementally from these sources, allowing an AI assistant to reuse repository knowledge without re-reading everything from scratch.

What is the best way to maintain a living project memory for an AI assistant?▼

The best way to maintain a living project memory is to use a persistent brain database that applies idempotent scans to capture new or changed files. This approach handles re-runs safely, deduplicates decisions, and updates the manifest after writes.

Does the project brain initialization support generating downstream knowledge articles?▼

Yes, the project brain initialization supports generating downstream knowledge articles. After the SQLite brain database is populated with indexed knowledge from scanned documentation, it can optionally generate knowledge-engine articles from the captured evidence.