Quick Start

One command.
Running in minutes.

Full install including all Python dependencies. No separate pip install. No Docker. No config files.

< 3 min

Install time

External deps to manage

Install

One pip command. Everything included.

terminal — install

# Install SuperLocalMemory (pip — everything included) $ pip install superlocalmemory
# Or upgrade to latest $ pip install -U superlocalmemory

Python 3.9+ required. All dependencies — CozoDB, LanceDB, sentence-transformers — install automatically.

Setup

Choose your operating mode in one interactive prompt.

terminal — setup

$ slm setup # Choose your mode: # A) Zero cloud — fully local, no LLM # B) Local Ollama — local LLM inference # C) Cloud LLM — OpenAI / Anthropic > Mode A selected. Initializing local database... ✓ SuperLocalMemory V3.6 ready. 0 facts indexed.

Mode A works out of the box with no API keys. See the Modes page for help choosing.

Your first memory

Store, recall, and check status — that's the full loop.

terminal — first memory

# Store your first memory $ slm remember "Alice works at Google as Staff Engineer" ✓ Stored → fact #1 · conf 0.97 · Mode A
# Recall it later $ slm recall "What does Alice do?" ↳ Staff Engineer at Google [conf 0.97 · 1 retrieval]
# Check system status $ slm status ✓ V3.6 · Mode A · 1 fact indexed · cache: on · math: active

You're done. Use slm --help to see all 26 data commands, each with --json output for agent pipelines.

Modes

Pick your mode.

Three modes, one install. You can switch at any time with slm setup --mode A.

Zero Cloud MODE A

No LLM needed.

TF-IDF embeddings, fastest install, fully offline. No API keys. No model downloads. Works instantly.

Best for: privacy-first teams, CI/CD pipelines,
any setup without GPU or API access.

$ slm setup --mode A

→ See Mode A docs

Local Ollama MODE B

Local LLM inference.

Ollama-powered semantic embeddings. Highest privacy with full semantic accuracy. All inference stays on your machine.

Best for: teams that want highest privacy
plus semantic recall accuracy. Needs Ollama + 4 GB RAM.

$ slm setup --mode B

→ See Mode B docs

Cloud LLM MODE C

Maximum accuracy.

OpenAI or Anthropic embeddings for the highest retrieval quality. API key required. Zero data stored externally.

Best for: max accuracy on large memory stores.
Needs an OpenAI or Anthropic API key.

$ slm setup --mode C

→ See Mode C docs

Verification

Confirm everything is running.

Three commands to verify your install is healthy.

terminal — verification

$ slm health ✓ daemon: running · db: healthy · cache: on · version: 3.6.0
$ slm status --json {"success": true, "version": "3.6.0", "mode": "A", "facts": 1, "cache_hits": 0}
$ slm --version superlocalmemory 3.6.0

Troubleshooting