Five years of daily AI use. Your system won't feel it. Infinite memory for Claude Code, Cursor, Windsurf & 17+ AI tools.

SuperLocalMemory gives AI assistants persistent memory across sessions. v3.6.11 "Optimize Everywhere" — cache, compress, and remember on any plan, no proxy required. No cloud. No APIs. No data leaves your machine.

Deploy SLM on a server and reach it from other machines. SLM_REMOTE=1 (default off) lets the dashboard load from a remote browser, lets MCP gateways/hubs forward tool calls, and makes custom local LLM endpoints (llama.cpp / LM Studio / Azure) configurable from the dashboard — plus a batch of stability and security fixes. LAN access stays gated by SLM_MCP_ALLOWED_HOSTS. See the Distributed Deployment guide.

Cache. Compress. Remember. SLM v3.6.11 delivers compression + caching across three surfaces: proxy (full-turn caching via slm wrap claude), MCP tools (5 new tools in slm mcp, full 1M window preserved), or skill (~/.claude/skills/slm-optimize/, zero-config auto-compress). Every setup covered — with or without a proxy. Install once with pip install -U superlocalmemory. View details →

Tiered storage auto-classifies every memory as active, warm, cold, or archived. Graph pruning removes redundant connections. Optional acceleration backends (CozoDB, LanceDB) for graph + vector operations. Tested on 1.18 million real graph edges with under 2-second recall. Migration is automatic: pip install -U superlocalmemory && slm restart. View details →

One npm install and your AI memory is fully automatic:

• Auto-recall at session start — your context is there before you ask
• Auto-observe during coding — decisions and changes captured silently
• Auto-save at session end — full summary with git context
• Zero setup — hooks install themselves, no config needed
• Zero risk — every hook fails silently, never blocks your workflow

SLM learns from your usage patterns and gets smarter over time — at zero token cost. Every recall generates learning signals. After 20+ signals, the system starts optimizing retrieval for YOUR specific patterns. After 200+, a full ML model trains on your data. No other memory system learns without spending LLM tokens. Read more →

npm install -g superlocalmemory # or: pip install superlocalmemory
slm setup # Choose mode A/B/C
slm warmup # Pre-download embedding model (optional)

That's it. Your AI now remembers you.