Automatic branch-specific CLAUDE.md memory management for Claude Code. When you switch git branches, your Claude Code context switches with you.
When working across multiple git branches, your CLAUDE.md file contains context specific to one branch. Switching branches means Claude Code loses that context, or worse, has the wrong context for your current work.
Branch Memory Manager saves and loads branch-specific CLAUDE.md files automatically. Each branch gets its own memory, stored in .claude/memories/.
As a Claude Code plugin — memories switch automatically when you run git checkout or git switch inside Claude Code. No manual intervention needed.
As a CLI — manually save, load, and manage branch memories from your terminal.
# Install the npm package in your project
npm install --save-dev claude-code-branch-memory-manager
# Or install globally
npm install -g claude-code-branch-memory-managerThen load as a plugin:
claude --plugin-dir ./node_modules/claude-code-branch-memory-managerOnce installed, branch memory switching happens automatically:
- You run
git checkout feature/authinside Claude Code - The plugin saves your current
CLAUDE.mdto.claude/memories/main.md - It loads
.claude/memories/feature_auth.mdintoCLAUDE.md - Claude Code now has the right context for your
feature/authwork
# Initialize in your repo
branch-memory init
# Save current context
branch-memory save "Implemented user auth"
# Switch branches (saves + loads automatically)
branch-memory switch feature/api
# List all saved memories
branch-memory list
# Check status
branch-memory status| Command | Description |
|---|---|
branch-memory save [description] |
Save current CLAUDE.md to branch memory |
branch-memory load <branch> |
Load memory from a specific branch |
branch-memory list |
List all stored branch memories |
branch-memory status |
Show current branch and memory status |
branch-memory switch <branch> |
Git switch + memory swap in one command |
branch-memory copy <src> <dst> |
Copy memory between branches |
branch-memory clean |
Remove memories for deleted branches |
branch-memory restore [branch] |
Restore from backup |
branch-memory init |
Set up branch memory in current repo |
branch-memory version |
Show version |
Branch memories are stored in .claude/memories/ within your repository:
your-repo/
├── CLAUDE.md # Active memory (read by Claude Code)
├── .claude/
│ └── memories/
│ ├── main.md # Memory for main branch
│ ├── feature_auth.md # Memory for feature/auth
│ ├── feature_api.md # Memory for feature/api
│ └── .backups/ # Automatic backups
│ └── main.2025-03-18T...md
When installed as a Claude Code plugin, two hooks handle automatic switching:
SessionStart— Loads the correct branch memory when Claude Code startsPostToolUse(Bash) — Detectsgit checkout/git switchcommands and swaps memories
When switching to a branch with no saved memory, the tool looks for a fallback in this order: main → master → develop. This is configurable.
Create a .branch-memory.json in your repo root:
{
"memoryDir": ".claude/memories",
"memoryFileName": "CLAUDE.md",
"autoSaveOnSwitch": true,
"fallbackToDefault": true,
"fallbackBranches": ["main", "master", "develop"]
}| Variable | Description |
|---|---|
BRANCH_MEMORY_DIR |
Memory storage directory |
BRANCH_MEMORY_FILE |
Memory file name |
BRANCH_MEMORY_AUTO_SAVE |
Enable/disable auto-save (true/false) |
BRANCH_MEMORY_FALLBACK |
Enable/disable fallback (true/false) |
BRANCH_MEMORY_FALLBACK_BRANCHES |
Comma-separated fallback branches |
When installed as a Claude Code plugin, these skills are available:
/branch-memory:save— Save current context/branch-memory:load— Load a branch's context/branch-memory:status— Show memory status/branch-memory:list— List all memories
- Add
.claude/memories/to.gitignoreif you don't want to share memories across the team - Commit
.claude/memories/if you want shared branch context - Run
branch-memory cleanperiodically to remove memories for deleted branches - Branch names are sanitized for filenames:
feature/authbecomesfeature_auth.md
- Node.js 18+
- Git 2.0+
MIT