back to home

matthiasn / lotti

AI-powered digital assistant that keeps your data private. Chat with your tasks, get intelligent summaries, and track what matters—all stored locally on your devices. Choose your AI provider per category or run everything offline. Your data, your control.

View on GitHub
1,088 stars
110 forks
5 issues

AI Architecture Analysis

This repository is indexed by RepoMind. By analyzing matthiasn/lotti in our AI interface, you can instantly generate complete architecture diagrams, visualize control flows, and perform automated security audits across the entire codebase.

Our Agentic Context Augmented Generation (Agentic CAG) engine loads full source files into context on-demand, avoiding the fragmentation of traditional RAG systems. Ask questions about the architecture, dependencies, or specific features to see it in action.

Source files are only loaded when you start an analysis to optimize performance.

Embed this Badge

Showcase RepoMind's analysis directly in your repository's README.

[![Analyzed by RepoMind](https://img.shields.io/badge/Analyzed%20by-RepoMind-4F46E5?style=for-the-badge)](https://repomind.in/repo/matthiasn/lotti)
Preview:Analyzed by RepoMind

Repository Overview (README excerpt)

Crawler view

Lotti **Your AI‑powered context manager — a private, local‑first assistant for your tasks, notes, and audio.** Lotti is an open-source personal assistant that helps you capture, organize, and understand your work and life through AI-enhanced task management, audio recordings, and intelligent summaries—all while keeping your data entirely under your control. Linux Users, Rejoice! Lotti is now available on Flathub — bringing AI-powered personal productivity to the Linux desktop! Blog Series: Meet Lotti The beginning of a **multi-part blog series with video walkthroughs** exploring everything Lotti can do is now live! From task management to AI-powered insights — learn how to take control of your productivity while keeping your data private. Start reading: **Meet Lotti** | **Project Background** Table of Contents • Why Lotti? • Example Use Cases • Core Features • AI-Powered Intelligence • Comprehensive Tracking • Privacy & Control • AI Provider Configuration • Getting Started • Installation • Beta Testing • Development • Documentation • Use Cases • For Developers • For Knowledge Workers • For Personal Growth • Contributing • Technical Stack • Philosophy • License • Acknowledgments Why Lotti? Most AI-powered tools require you to upload and store your personal data on their servers, creating privacy risks and vendor lock-in. Lotti takes a different approach: • **Complete data ownership**: Your information stays on your devices. When you opt into cloud inference, European‑hosted, no‑retention providers are available • **Configurable AI providers per category**: Choose between OpenAI, Anthropic, Gemini, Ollama (local), or any OpenAI-compatible provider on a per-category basis • **Privacy-first design**: You control exactly what data gets shared with AI providers—only for specific inference calls via your API keys • **No vendor lock-in**: Your data remains portable and accessible, independent of any subscription Example Use Cases • Pick up a task from last week — see your last notes, time spent, and a one‑paragraph recap • Record a quick voice note — later it’s transcribed and turned into a checklist • Ask “What did I finish in June?” — get a dated list with brief summaries Core Features *Currently, Lotti's AI capabilities are focused on task management and productivity. Habit tracking is fully functional but will receive AI enhancements in future updates.* 🤖 AI-Powered Intelligence • **Smart Summaries**: Automatically generate summaries of tasks, capturing key points and progress • **Audio Transcription**: Transcribe recordings using either local Whisper (OpenAI's open weights model, 99 languages supported) or cloud providers with audio capabilities like Gemini Flash/Pro • **Context Recap**: Resume a task with a one‑screen recap of your latest notes, time, and progress • **Intelligent Checklists**: Transform rambling audio notes into actionable checklists • **Chat with Your Data**: Ask questions about your tasks, learnings, and achievements across any time period 📝 Comprehensive Tracking • **Tasks**: Full lifecycle management (open, groomed, in progress, blocked, done, rejected) • **Audio Recording**: Capture thoughts, progress notes, and brain dumps • **Time Tracking**: Record time spent on tasks and projects • **Journal Entries**: Written reflections and documentation • **Habits**: Define and monitor daily habits and routines • **Health Data**: Import from Apple Health and other sources • **Custom Metrics**: Track anything that matters to you 🔐 Privacy & Control • **Local-Only Storage**: All data is permanently stored only on your devices and never in the cloud • **Encrypted Sync**: End-to-end encrypted synchronization between your devices (desktop/laptop and mobile) using **Matrix** (requires a Matrix account — self-hosted or public homeserver) • **Selective AI Usage**: Configure AI providers per category—keep sensitive data completely local with Ollama but use state‑of‑the‑art (frontier) cloud models when appropriate • **Your API Keys**: When you choose cloud AI, data is shared only for that specific inference call. Please review the respective provider's terms and privacy policy to understand how they handle your data • **GDPR-Compliant Options**: European-hosted AI providers with no data retention policies available for enhanced privacy • **Built for on‑device**: Designed for the era when local AI inference becomes standard AI Provider Configuration Lotti supports multiple AI providers, configurable per category: • **Cloud Providers**: OpenAI, Anthropic Claude, Google Gemini • **Local Inference**: Ollama for complete privacy (requires capable hardware) • Full functionality available with local models like Qwen3 (8B), GPT-OSS (20B/120B), Gemma3 (12B/27B) • Combined with local Whisper for speech recognition, enables 100% offline AI capabilities • **OpenAI-Compatible**: Any provider with OpenAI-compatible APIs • **European Options**: GDPR-compliant hosted alternatives Configure different providers for different aspects of your life—use cutting-edge models for work projects while keeping personal reflections completely private with local inference. With sufficient hardware, you can run everything locally without any cloud dependency. Getting Started Installation See DEVELOPMENT.md for setup and development workflow. Beta Testing • **Build it yourself**: for iOS, macOS, Android, Linux, Windows • **iOS/macOS**: TestFlight builds are available for select users, will be available more broadly in due course • **Linux**: See files on **GitHub releases** - will also be available via Flatpak soon Development • Install Flutter (instructions) — FVM recommended; repo includes • Install dependencies: • **Linux only**: Install emoji font support for proper emoji rendering: • Static analysis: • Tests: • Coverage report: • Code generation: • Localization: • Run locally: macOS • others See DEVELOPMENT.md for detailed development setup. Documentation Getting Started Guides • Gett…