/brain:init

Initialize the ~/.brain/ directory structure with default categories and supporting files.

Usage

/brain:init

No arguments required.

What It Does

Running /brain:init creates the complete brain directory structure in your home folder:

~/.brain/
├── index.json              # Memory inventory — fast lookup for all memories
├── associations.json       # Weighted associative network between memories
├── contexts.json           # Session context snapshots
├── review-queue.json       # Spaced repetition scheduling
├── professional/           # Work, career, technical skills
│   └── _meta.json
├── personal/               # Education, health, hobbies, goals
│   └── _meta.json
├── social/                 # Communities, networks, collaborations
│   └── _meta.json
├── family/                 # Family relationships and events
│   └── _meta.json
├── _consolidated/          # Merged memories from consolidation
│   └── _meta.json
└── _archived/              # Decayed memories (recoverable + searchable)
    ├── _meta.json
    └── index.json          # Searchable archive index

Files Created

• index.json — The central registry that tracks all memories, their locations, types, strengths, and metadata. Also contains the brain configuration under the config key.
• associations.json — The associative network graph. Starts empty and grows as memories are created and recalled together.
• contexts.json — Session context snapshots used for context-dependent recall. Stores the last 20 session summaries.
• review-queue.json — Spaced repetition queue generated during /brain:sleep. Starts empty.

Directories Created

• professional/ — Work, career, technical skills. Subcategories like companies/, skills/, career/ are created on demand.
• personal/ — Education, health, hobbies, personal goals. Subcategories created on demand.
• social/ — Communities, networks, collaborations.
• family/ — Family relationships and events.
• _consolidated/ — Where merged memories from consolidation are stored.
• _archived/ — Where decayed memories are moved during sleep. They remain searchable.

Each directory contains a _meta.json file that tracks category-level statistics (memory count, average strength, last updated).

Default Configuration

The index.json file includes a config section with default settings:

{
  "config": {
    "max_depth": 6,
    "consolidation_threshold": 0.3,
    "decay_check_interval_days": 7,
    "strength_boost_on_recall": 0.05,
    "auto_consolidate": true,
    "propagation_window_days": 7,
    "association_config": {
      "co_retrieval_boost": 0.10,
      "link_decay_rate": 0.998,
      "link_prune_threshold": 0.05,
      "spreading_activation_depth": 2,
      "spreading_activation_decay": 0.5
    }
  }
}

See Configuration for a full description of each setting.

Re-Running Init

If ~/.brain/ already exists, running /brain:init again is safe. The agent will:

• Create any missing directories or files
• Preserve all existing memories and configuration
• Not overwrite existing data

Example Interaction

User: /brain:init

Agent: I've initialized your brain at ~/.brain/

Created directory structure:
  ├── professional/
  ├── personal/
  ├── social/
  ├── family/
  ├── _consolidated/
  └── _archived/

Created supporting files:
  ├── index.json (with default configuration)
  ├── associations.json
  ├── contexts.json
  └── review-queue.json

Your brain is ready. Start memorizing with /brain:memorize