
Install the plugin
Requires Node.js 18+ on your PATH — the memory hooks run as Node scripts.
Migrating from the old
claude-supermemory plugin name? It was renamed to supermemory and will not update in place:Authenticate
Start a Claude Code session and the plugin opens a browser login, then saves the key to~/.supermemory-claude/credentials.json.
Or create a Supermemory API key from the API Keys page in the console and add it to your shell profile:
- macOS / Linux (zsh)
- macOS / Linux (bash)
- Windows (PowerShell)
How it works
Once installed, the plugin runs automatically:- Session context — At session start, profile facts for this project are loaded into context.
- Direct recall — Before Claude sees each substantive prompt, the hook searches Supermemory and injects fresh matches. Set
recallDirectiveto switch to advisory mode, where Claude decides when to search. - Auto-capture — After each Claude response (the Stop hook), conversation content added since the last save is captured in the background.
- Shared repo memory — Captures go to one repository container shared with the Codex, OpenCode, and Cursor plugins, tagged with
sm_scope: personalmetadata. - MCP tools — The hosted Supermemory MCP tools (
search_memory,add_memory, and more) use the same credentials.search_memoryand the legacy camelCase read tools (listMemories,listDocuments,getDocument,listSpaces,whoAmI) are approved automatically; other tools, includinglist_memories,list_documents,get_documentandget_profile, still ask for approval. For deeper history, Claude can also use thecontext-gathereragent.
Commands
Configuration
Environment variables
Global settings
Create~/.supermemory-claude/settings.json:
Project config
Per-repo overrides in.claude/.supermemory-claude/config.json. Create the file manually:
API key precedence is
SUPERMEMORY_CC_API_KEY, project apiKey, then ~/.supermemory-claude/credentials.json.
Next steps
GitHub repository
Source code, issues, and detailed README.
Cursor plugin
Memory for your Cursor chats.