claude-brain
Sync your Claude Code brain across machines — memory, skills, agents, rules, and settings with intelligent semantic merge.
The Problem
You use Claude Code on multiple machines. Your laptop has learned your coding patterns. Your desktop has custom skills. None of them talk to each other. Every time you switch machines, you lose context and re-teach Claude the same things.
The Solution
# Machine A (work laptop)
> /brain-init git@github.com:you/my-brain.git
✓ Brain exported: 42 memory entries, 3 skills, 5 rules
✓ Pushed to remote
# Machine B (home desktop)
> /brain-join git@github.com:you/my-brain.git
✓ Pulled brain, merged with local state
✓ Auto-sync enabled — your brain follows you.Two commands. Zero daily effort. Works forever.
Key Features
Auto-sync
Hooks run on every session start/end
Hooks run on every session start/end
Semantic Merge
LLM-powered dedup of memory & CLAUDE.md
LLM-powered dedup of memory & CLAUDE.md
Cross-machine
Laptop + desktop + cloud VM all converge
Laptop + desktop + cloud VM all converge
Encryption
Optional age encryption at rest
Optional age encryption at rest
Team Sharing
Share skills, agents, rules with teammates
Share skills, agents, rules with teammates
Security-first
Secrets stripped, env vars excluded
Secrets stripped, env vars excluded
Get Started
⭐ View on GitHub Quick Start Guide →Why claude-brain?
No other tool does cross-machine semantic merge of Claude Code's brain state. Unlike dotfile managers that just copy files, claude-brain intelligently merges your Claude Code memory, resolves contradictions, and deduplicates knowledge — all via Git, with no central server.
MIT License · GitHub