🔰 Goal
To build a modular, open infrastructure for natural AI communication. The vision: a system that intelligently combines speech, image, and context – across local and remote nodes.
🧱 Core Modules (Nova AI Brainpool Plugin)
| Status | Version | Module | Description |
|---|---|---|---|
| ✅ | v23 | Stable Base | Admin panel, chat, console, API integration (Ollama, .env, Zephyr) |
| ✅ | v24 | Image Generation | Stable Diffusion API support, prompt recognition, chat integration |
| ✅ | v25 | NovaNet Core | Local node communication, prompt exchange, memory storage (JSON-based) |
| 🧪 | v26 | Voice Control (Local) | Whisper integration for voice-to-text commands (offline) |
| 🔜 | v27 | NovaNet Remote | Distributed AI communication over WebSockets or REST endpoints |
| 🖼 | v28 | Image Understanding (LLaVA) | Vision module for analyzing and describing uploaded images |
🧠 Technologies & Components
- Language: Whisper (offline), Text2Prompt logic
- Image: Stable Diffusion WebUI, optional SDXL
- Communication: NovaNet JSON protocol (REST / WebSocket)
- Admin Console: WordPress plugin with CLI compatibility
- Crawler Module: Autonomous data gathering & knowledge caching
- System API: Diagnostic logs, vision uploads, `aiscan` hooks
📌 Focus – July 2025
- 📱 Release of Android Beta (WebView-based Cordova app)
- 🧩 Finalized session system & image generation flow
- 🎨 Image saving under Android (Scoped Storage fixes in progress)
- 📡 NovaNet v25 live – JSON exchange & memory sharing enabled
- 🛠 Claude-powered plugin architecture refactoring
- 🌐 New webpage: What We Achieved Yet with full status overview
💡 Vision (by end of 2025)
“Nova thinks, sees, speaks and evolves – with every node that joins.”