Lotti

About

Lotti gives you a private logbook and a staff of personal AI assistants to go with it. Record your day the way it actually happens — tasks, tracked time, voice notes, transcriptions, journal entries, habits, and health data — and long-living agents read what you record, keep it summarised, remember the context you would otherwise lose, and propose the next step. Agents suggest, you decide: every proposed change waits for your approval, with one small exception — an initial title or language for an otherwise empty task.

All of it happens on your own devices. No server ever holds your data in readable form: multi-device sync is end-to-end encrypted, and the relay between your verified devices holds only ciphertext — not forever, and nothing depends on it keeping anything. There is no telemetry. On capable hardware the AI models run locally too, so your data never has to leave the machine; on lighter hardware, or to save battery, you route inference — per life category — to a cloud provider you choose. Your logbook is ordinary SQLite on your own disk with attachments in ordinary files beside it, readable without Lotti, so there is nothing to export and nothing to unlock.

Under the hood, sync runs over Matrix using Vodozemac (Rust) for Megolm crypto; the homeserver relays only ciphertext between your own devices, and encryption keys reach only devices you have verified. A new device catches up because your other devices re-send history, not because a server stored it.

Get support and join the Lotti community on Discord via the Contact link.

What it does:

• Long-living AI agents (mission, soul, report directive) that read your logbook, propose changes, and only act after you approve
• Two-database architecture: a strict separation between your facts (the user database) and what the agents think (the agentic database), enforced on disk
• Run reasoning-capable models locally via oMLX or Ollama (e.g. Qwen 3.6 35B A3B, a Mixture-of-Experts model with ~3B active parameters) — or use Gemini Flash, OpenAI, Anthropic, Mistral, Melious.ai, or any OpenAI-compatible cloud provider, on a per-category basis
• Local voice transcription with Whisper or Voxtral; cloud transcription via Gemini, OpenAI, Mistral, or Melious.ai
• AI-generated cover art for tasks via Nano Banana Pro on Gemini, OpenAI, or Qwen, and Flux on Melious.ai
• Both the logbook and the agentic state sync end-to-end encrypted
• Habit tracking with success/fail/skip completion types, custom measurables, and dashboards
• Bring-your-own API keys for cloud providers, choosing per category where inference happens — EU-hosted, US, Chinese, or entirely on your own machine
• Usage & Impact: tokens and requests for every cloud AI call, broken down by category and model, plus cost, energy and CO2e wherever the provider reports them (currently Melious); local inference is not measured
• Time recording kept separate from planning, so what you meant to do and what actually happened stay distinct facts