amemor-ai®
Local-first

Your data stays on your hardware

SQLite-backed, zero cloud dependencies — runs on everything from a Raspberry Pi to enterprise servers.

On your machine

Local-first storage — your data is processed and kept only on your own hardware.

No cloud dependency

SQLite-backed engine: no servers, no Docker, no cloud accounts required.

Runs anywhere

From a Raspberry Pi to enterprise servers — install detects your hardware and picks a local model.

← Back to home

Under the hood

The technical capabilities behind this — from the live feature inventory.

Per-user DB sharding

16 live shards (141k rows) + a team shard + fan-out search — isolation is structural, not a filter you can forget to apply.

RAW layer + sandbox

Append-only raw ingest with bwrap/seccomp sandbox promotion and full RAW→SQL provenance (two-hash contract).

Any LLM, local or cloud

One router speaks local Ollama (offline, GPU-aware), OpenRouter and native SDKs with automatic fallback — your data still stays local.

Hardware-aware bootstrap

Install detects OS/GPU/VRAM and chooses a local model; pip install uaml-memory, no cloud accounts.

Start free, scale when ready

Free engine on your own hardware. No credit card. Found­er pricing through 31 October 2026.

View pricing Back to home