Cross-Agent Memory Sharing

Brain Memory uses a single global directory — ~/.brain/ — that is shared across all supported AI agents. A decision stored by Claude Code in one project is immediately available to Gemini CLI or OpenAI Codex CLI in any other project, with no configuration, no export, and no per-project setup.

How It Works

All three supported agents read and write to the same ~/.brain/ directory:

~/.brain/                          ← Single shared directory
├── index.json                     ← Shared index
├── associations.json              ← Shared associative network
├── contexts.json                  ← Session contexts from all agents
├── professional/
│   └── decisions/
│       └── chose-kafka.md         ← Created by Claude Code
├── personal/
│   └── education/
│       └── rust-ownership.md      ← Created by Gemini CLI
└── ...

The format is agent-agnostic: plain Markdown files with YAML frontmatter. Any tool that can read Markdown can read your brain.

Agent-Agnostic Format

Brain Memory deliberately avoids any agent-specific constructs:

No vendor lock-in. No proprietary binary formats. Your memories are yours.

What Gets Shared

Everything in ~/.brain/ is automatically shared:

• Memories — All memory files, regardless of which agent created them
• Associations — The full associative network, including links created by different agents
• Index — The central registry with all memory metadata
• Configuration — Brain settings apply to all agents uniformly
• Review queue — Spaced repetition schedule works across agents
• Contexts — Session context history from all agents (labeled by source)

What Does Not Get Shared

• Agent configuration — Each agent's command prompts and prompt sections are installed separately in their own config directories (~/.claude/, ~/.gemini/, ~/.codex/)
• Session state — Each agent maintains its own session context during active use
• Sync state — The ~/.brain/.sync/ directory is local and agent-independent

Cross-Agent Scenarios

Scenario 1: Claude Code creates, Gemini CLI recalls

1. You work on a project with Claude Code and run /brain:memorize
2. Claude Code stores a decision memory in ~/.brain/professional/
3. Later, you open a different project with Gemini CLI
4. Gemini CLI loads the brain at session start and sees the memory
5. When the topic comes up, Gemini CLI references it naturally

Scenario 2: Multiple agents in the same session

1. You use Claude Code to analyze a codebase and memorize findings
2. You switch to Gemini CLI for a different task in the same project
3. Both agents share the same brain — Gemini sees what Claude stored
4. Gemini CLI adds its own memories, which Claude Code will see next time

Scenario 3: Review queue across agents

1. /brain:sleep is run from Claude Code, populating the review queue
2. You open Gemini CLI and run /brain:review
3. The review session uses the same queue generated by Claude Code
4. Recalled memories are reinforced regardless of which agent does the review

No Configuration Needed

Cross-agent sharing requires no setup beyond installing Brain Memory for each agent. Since all agents read from and write to ~/.brain/, sharing is automatic.

The only requirement is that each agent has its own command prompts installed. During installation, you can choose to install for multiple agents at once:

npx brain-memory@beta --all --global

This installs command prompts for Claude Code, Gemini CLI, and OpenAI Codex CLI simultaneously, all pointing to the same ~/.brain/ directory.

Human Access

Because the format is plain Markdown, you can also browse and edit your brain directly:

• Open ~/.brain/ in VS Code, Obsidian, or any file explorer
• Read memory files with any text editor
• Search across memories with grep or your editor's search
• Edit memories manually if needed (be careful with frontmatter format)
• Use Git to track changes: cd ~/.brain && git init && git add -A && git commit -m "snapshot"

Your brain is not locked inside any tool — it is always accessible.