-
-
Notifications
You must be signed in to change notification settings - Fork 24
Home
Varun Pratap Bhardwaj edited this page Mar 16, 2026
·
38 revisions
Your AI Finally Remembers You. 100% local. Zero setup. Completely free.
SuperLocalMemory gives AI assistants persistent memory across sessions. Install once, and your AI remembers your projects, preferences, decisions, and debugging history — forever.
npm install -g superlocalmemory slm setup
That's it. Your AI now remembers you.
| Mode | What It Does | Cloud Required |
|---|---|---|
| A: Local Guardian | Zero cloud. Your data never leaves your machine. EU AI Act compliant. | No |
| B: Smart Local | Local LLM via Ollama for answer synthesis. Still fully private. | No |
| C: Full Power | Cloud LLM for maximum accuracy (87.7% on LoCoMo benchmark). | Yes |
- Works in 17+ IDEs — Claude Code, Cursor, VS Code, Windsurf, Gemini CLI, JetBrains, and more
- Auto-capture — Decisions, bug fixes, and preferences stored automatically
- Auto-recall — Relevant context injected before your AI responds
- 4-channel retrieval — Semantic + keyword + entity graph + temporal for maximum accuracy
- Mathematical foundations — Information-geometric similarity, consistency checking, self-organizing lifecycle
- Trust scoring — Bayesian trust per agent and per fact
- EU AI Act compliant — Mode A satisfies data sovereignty by architecture
- Multi-profile — Isolated memory contexts for work, personal, clients
| Page | What You'll Learn |
|---|---|
| Getting Started | Install + first memory in 5 minutes |
| Modes Explained | A vs B vs C — which is right for you |
| CLI Reference | All slm commands with examples |
| MCP Tools | All 24 MCP tools for IDE integration |
| IDE Setup | Per-IDE configuration guide |
| Migration from V2 | Upgrade guide for existing users |
| Auto-Memory | How auto-capture and auto-recall work |
| Architecture Overview | How the system works |
| Mathematical Foundations | The math behind the memory |
| Compliance | EU AI Act, GDPR, retention policies |
| FAQ | Common questions answered |
- V3 Paper: Information-Geometric Foundations for Agent Memory (Zenodo)
- V2 Paper: Privacy-Preserving Multi-Agent Memory (arXiv)
Part of Qualixar | Created by Varun Pratap Bhardwaj
SuperLocalMemory V3
Getting Started
Reference
Architecture
Enterprise
V2 Documentation