A Claude Code plugin that gives your AI persistent memory across sessions using Supermemory. Your agent remembers what you worked on - across sessions, across projects.

• Team Memory — Project knowledge shared across your team, separate from personal memories
• Auto Capture — Conversations saved when session ends
• Project Config — Per-repo settings, API keys, and container tags

Requires Node.js 18+ on your PATH — the memory hooks run as Node scripts.

/plugin marketplace add supermemoryai/claude-supermemory
/plugin install supermemory

Already have the old claude-supermemory plugin installed? It was renamed to supermemory, so it won't update in place. Migrate with:

/plugin marketplace update supermemory-plugins
/plugin install supermemory@supermemory-plugins

Then, only if you still have the old plugin, remove it:

/plugin uninstall claude-supermemory@supermemory-plugins

Set your API key (get one at app.supermemory.ai):

export SUPERMEMORY_CC_API_KEY="sm_..."

• Reasoned recall — Before each turn, Claude decides whether recalling memory would actually help your current message, and only searches when it's worth it — every turn, once in a while, or not at all. The search runs automatically (no permission prompt), just like auto-capture. Searching only when needed also keeps more usage on your plan
• supermemory-search — Ask about past work or previous sessions, Claude searches your memories
• supermemory-save — Ask to save something important, Claude saves it for the team

Claude Code, Codex, and OpenCode use one container for a repository:

• repo_<project-name>__<remote-hash> stores automatic capture and every explicit save.
• sm_scope metadata keeps personal and project memories filterable inside that container.

The hash is derived from the normalized Git remote, so clones share memory while same-named repositories do not collide. Repositories without a remote fall back to a local path identity. The agent plugins also read the previous user_project_*, repo_<project-name>, claudecode_project_*, codex_user_*, codex_project_*, opencode_user_*, and opencode_project_* containers, so existing memories remain searchable without a migration. Set SUPERMEMORY_ISOLATE_WORKTREES=true to use the worktree path instead of the remote identity.

Explicit repoContainerTag/projectContainerTag overrides remain the canonical write destination. Older personal/user overrides remain in the legacy read set.

Environment

SUPERMEMORY_CC_API_KEY=sm_...    # Required
SUPERMEMORY_DEBUG=true           # Optional: enable debug logging

Global Settings — ~/.supermemory-claude/settings.json

{
  "maxProfileItems": 5,
  "signalExtraction": true,
  "signalKeywords": ["remember", "architecture", "decision", "bug", "fix"],
  "signalTurnsBefore": 3,
  "includeTools": ["Edit", "Write"]
}

Project Config — .claude/.supermemory-claude/config.json

Per-repo overrides. Run /supermemory:project-config or create manually:

{
  "apiKey": "sm_...",
  "baseUrl": "https://api.supermemory.ai",
  "repoContainerTag": "my-team-project",
  "signalExtraction": true
}

For information about how Supermemory collects, uses, and retains data, see the Supermemory Privacy Policy.

MIT