Live Demo

See it
in action.

Real commands. Real output. No fabricated benchmarks — these are the actual CLI interactions SLM performs locally on your machine.

Watch the Demo

SuperLocalMemory in 5 minutes.

Full walkthrough — install, setup, recall, cache, and compression in one take.

Interactive Demo

Pick a capability.

Three core commands, live. Click a tab to switch — the terminal replays the actual interaction in real time.

superlocalmemory — interactive demo
Use Cases

Built for how you actually work.

Whether you're on a team, solo, or building agents — SLM slots into your workflow without friction.

01 · Engineering Teams

Engineering Teams

Persist architecture decisions, API contracts, and bug resolutions across sessions. Never re-explain context to a new agent session.

$ slm remember "API rate limit: 100 req/min per user, burst 200" ✓ Stored → #4,901 · conf 0.98 $ slm recall "API limits" ↓ rate: 100/min, burst: 200 [conf 0.98]
02 · Solo Developers

Solo Developers

Build a searchable memory of everything you've ever debugged, decided, or documented. Your personal engineering knowledge base.

$ slm recall "how did we fix the CORS issue last month?" ↓ Added Origin header allowlist in nginx.conf [conf 0.94]
03 · AI Agent Pipelines

AI Agent Pipelines

Give your autonomous agents persistent context that survives session boundaries. Zero cloud dependency in the data path.

$ slm recall "current sprint goal" --json {"data": {"fact": "ship auth refactor by June 30", ...}}
Benchmark Results

Measured. Published. Reproducible.

Every number here appears in a peer-reviewed paper. Nothing hand-picked, nothing cherry-picked.

74.8%
LoCoMo (Mode A)
LOCAL-FIRST · ZERO CLOUD
87.7%
LoCoMo (Mode C)
FULL POWER · CLOUD LLM
60–95%
Compression ratio
EXTRACTIVE · BYTE-EXACT REVERSIBLE
$0
Cost per cache hit
EXACT-MATCH · SESSION TTL

LoCoMo is a long-context conversation memory benchmark. Results published in arXiv:2603.14588.

Quick-Start Configs

Zero-config integration.

Three lines or fewer to connect SLM to your tool of choice. Copy, paste, done.

// .claude/settings.json "mcpServers": "superlocalmemory": "command": "slm", "args": ["mcp-server"]
// ~/.cursor/mcp.json "mcpServers": "superlocalmemory": "command": "slm", "args": ["mcp-server"]
# Add to ~/.zshrc or ~/.bashrc alias remember='slm remember' alias recall='slm recall' # Then just: remember "Alice owns the auth service" recall "who owns auth?"

Ready to try it?

One command to install. Local-first by default. No cloud dependency.