Getting Started

June 11, 2026 · View on GitHub

SuperLocalMemory V3 Documentation https://superlocalmemory.com | Part of Qualixar

Get your AI's memory system running in under 5 minutes. V3.1: Now with Active Memory — your memory learns from your usage and gets smarter over time, at zero token cost.

Why not just use Claude's built-in memory?

Anthropic's free Claude Memory (March 2026) and Claude Code's Auto-Memory are fine defaults. SLM earns the daemon in three places:

Local-only by default. Your memory never leaves your laptop — no cloud sync, no vendor lock-in. (Opt-in skill evolution is the only outbound path, and it is off by default.)
Shared across tools, not just one chat. One memory, consumed by Claude Code + Cursor + Antigravity + VS Code + Claude Desktop — anything that speaks MCP.
Learns from your outcomes. Implicit reward signals (dwell, re-query, edit, cite) retrain the ranker against how you actually work, not just summarised chat transcripts.

SuperLocalMemory is built for one developer, one laptop, many tools. Team / multi-user memory is a different product (SLM-Mesh).

Integration surface: MCP-native. The five IDEs listed below are explicit wirings, but any MCP-compatible client (LangChain-MCP adapters, LlamaIndex MCP, CrewAI-via-MCP, etc.) can use SLM without a custom adapter.

Prerequisites

Node.js 18 or later
Python 3.11 or later — macOS ships 3.9; use brew install python@3.11 or a version manager. Ubuntu 22.04 users: sudo add-apt-repository ppa:deadsnakes/ppa && sudo apt install python3.11 python3.11-venv
An AI coding tool (Claude Code, Cursor, VS Code, Windsurf, or any MCP-compatible IDE)

Linux / Ubuntu 22.04: Install in a venv to avoid system-Python conflicts:
python3.11 -m venv ~/.slm-venv && source ~/.slm-venv/bin/activate
pip install superlocalmemory
Then set SLM_PYTHON=~/.slm-venv/bin/python so slm uses that interpreter.

Install

npm install -g superlocalmemory

This installs the slm command globally.

Run the Setup Wizard

slm setup

The wizard walks you through three choices:

Pick your mode
- Mode A (default) — Zero cloud. All memory stays on your machine. No API key needed.
- Mode B — Local LLM. Uses Ollama on your machine for smarter recall.
- Mode C — Cloud LLM. Uses OpenAI, Anthropic, or another provider for maximum power.
Connect your IDE — The wizard detects installed IDEs and configures them automatically.
Verify installation — A quick self-test confirms everything works.

Tip: Start with Mode A. You can switch to B or C anytime with slm mode b or slm mode c.

Store Your First Memory

slm remember "The project uses PostgreSQL 16 on port 5433, not the default 5432"

You should see:

Stored memory #1 (Mode A, profile: default)

Recall a Memory

slm recall "what database port do we use"

Output:

[1] The project uses PostgreSQL 16 on port 5433, not the default 5432
    Score: 0.94 | Stored: 2 minutes ago | Profile: default

Check System Status

slm status

This shows:

Current mode (A, B, or C)
Active profile
Total memories stored
Database location
Health of math layers (Fisher, Sheaf, Langevin)

How It Works With Your IDE

Once connected, SuperLocalMemory works automatically:

Auto-recall — When your AI assistant responds, relevant memories are injected as context. No manual queries needed.
Auto-capture — Decisions, bug fixes, architecture choices, and preferences are stored as you work. No manual tagging needed.

You can still use slm remember and slm recall from the terminal whenever you want explicit control.

Next Steps

What you want to do	Guide
Set up a specific IDE	IDE Setup
Switch modes or providers	Configuration
Learn all CLI commands	CLI Reference
Migrate from V2	Migration from V2
Understand how it works	Architecture