Friday – A voice-activated personal AI companion built with Flutter

Developer dj2313 released Friday Assistant, an open-source voice-activated personal AI companion built with Flutter that runs on Android, iOS, Web, and Desktop. Friday Assistant pairs Groq's Llama 3.3 70B model for inference with a Supabase PostgreSQL vault for long-term memory, and adds a Proactive Sentinel Mode for scheduled background checks on schedule, weather, and environment. The project requires Flutter SDK v3.10+, a Supabase project with chat_messages and Friday_memory tables, and a Groq API key, and is installed via git clone of the jarvis_assistant repository followed by flutter pub get and flutter run.

Friday Assistant is a next-generation, voice-activated Personal AI companion built with Flutter . Designed with a "Sci-Fi First" philosophy, it combines state-of-the-art Large Language Models LLMs with a premium, immersive user interface featuring holographic aesthetics, reactive animations, and proactive intelligence. Unlike standard chatbots, Friday possesses Long-Term Memory , Real-Time Web Access , and a Proactive Sentinel Mode that watches out for you even when the app is in the background. | Feature | Benefit | |---|---| | Voice-first interface | Hands-free operation | | Long-term memory | Remembers your preferences across sessions | | Proactive notifications | Alerts you before conflicts arise | | Tool integration | Opens apps, sends messages, navigates | | Multi-platform | Android, iOS, Web, Desktop | | Privacy-focused | Your data stays in your Supabase vault | - The Friday Orb: A central, living core that reacts to voice amplitude, pulses when thinking, and transforms based on AI state Idle, Listening, Processing, Speaking - Holographic Aesthetics: Glassmorphism effects, neon gradients, and dynamic Particle Field backgrounds - Neural HUD: Real-time system status display with Neural Link indicator and active Memory Node count - Immersive Feedback: Haptic feedback and distinct sound effects for all interactions - FridayBrainService: Powered by Groq Llama 3.3 70B for lightning-fast inference and complex reasoning - Agentic Workflow: Visualized thought process phases: Thinking - Searching Web - Accessing Memory - Synthesizing - Memory Auditor: Autonomous sub-agent that verifies information against existing memory to prevent conflicts - Tool Integration: - web search: Real-time data fetching Weather, News, Stock Prices - save memory/search memory: Supabase Vault integration for personal facts and preferences - Background Nudges: Scheduled background checks on schedule, weather, and environment - Contextual Awareness: Intelligent notifications e.g., "Outdoor meeting at 3 PM with forecasted rain - take an umbrella" - Manual Diagnostics: Trigger instant Sentinel Check for immediate analysis - Multilingual Support: English, French, German, Spanish, and Hindi - Real-Time Transcription: Seamless speech-to-text dictation - Natural Voice: High-quality Text-to-Speech response system - Local Processing: Initial reasoning via Groq's high-speed inference - Encrypted Vault: Personal memories in private Supabase instance with Row Level Security RLS - Minimal Footprint: No audio data storage; STT processed and discarded in real-time | Component | Technology | |---|---| | Framework | Flutter Dart | | AI Backend | Groq API Llama 3.3 70B | | Database | Supabase PostgreSQL | | State Management | Native setState & Streams | | Animations | flutter animate & Custom Painters | | Voice | speech to text & flutter tts | | Background Tasks | workmanager | | Notifications | flutter local notifications | - Flutter SDK v3.10+ installed - Supabase Project with chat messages and Friday memory tables - Groq API Key for LLM inference 1. Clone the Repository git clone https://github.com/dj2313/jarvis assistant.git cd jarvis assistant 2. Configure Environment Create a .env file in the root directory: GROQ API KEY=your groq api key here SUPABASE URL=your supabase url here SUPABASE ANON KEY=your supabase anon key here 3. Install Dependencies flutter pub get 4. Run the App flutter run lib/ ├── core/ Configuration and Constants ├── models/ Data Models ChatMessage, etc. ├── screens/ UI Screens │ ├── friday home screen.dart Main HUD Interface │ ├── friday initialization screen.dart Boot-up Sequence │ └── ... ├── services/ Logic & API Layers │ ├── friday brain service.dart AI Core, Groq Integration, & Tools │ ├── memory service.dart Supabase DB Interactions │ └── vocal service.dart TTS & STT Handling └── widgets/ Reusable UI Components └── friday orb.dart The animated AI Core Contributions are welcome See CONTRIBUTING.md https://github.com/dj2313/jarvis assistant/blob/main/CONTRIBUTING.md for guidelines. This project is licensed under the MIT License - see LICENSE https://github.com/dj2313/jarvis assistant/blob/main/LICENSE for details. If you find this project useful, please give it a star Built with love for the Future.