{"slug": "show-hn-assistantai-real-time-conversation-hints-and-screenshot-analysis", "title": "Show HN: AssistantAI – Real-Time Conversation Hints and Screenshot Analysis", "summary": "A developer released AssistantAI, an open-source desktop AI assistant that captures audio from apps like Zoom and Teams, generates context-aware responses using attached documents, and analyzes screenshots via a web interface. Built with Python, it uses ScreenCaptureKit, Silero VAD, and whisper.cpp for low-latency speech processing.", "body_md": "A real-time desktop AI assistant.\n\nAssistantAI listens to a selected application (Zoom, Teams, Telegram, browsers, and other apps), detects spoken conversations, generates context-aware responses using an attached document and can analyze screenshots through its built-in web interface.\n\nBuilt as a personal engineering project to explore low-latency desktop AI, speech processing, context-aware conversations and screenshot analysis.\n\n- Application-specific audio capture using ScreenCaptureKit\n- Voice activity detection (Silero VAD)\n- Local speech recognition with whisper.cpp\n- Context-aware conversations using an attached document\n- Screenshot capture and AI analysis\n- Local conversation history\n- Remote web interface\n\nThe current implementation is written in Python.\n\nUseful starting points:\n\n- Python setup:\n`bash python/run/setup_python_env.sh`\n\n- Python docs:\n`python/README.md`\n\n- Audio capture research:\n`docs/modules/audio-capture-research.md`\n\nAdditional implementation details, installation instructions, and OpenAI configuration are available in python/README.md.\n\nFuture versions may include additional components and languages as the project evolves.\n\n- Additional LLM backends (Ollama, llama.cpp)\n- Additional document formats\n- Improved screenshot analysis", "url": "https://wpnews.pro/news/show-hn-assistantai-real-time-conversation-hints-and-screenshot-analysis", "canonical_source": "https://github.com/Aleksandern/assistant-ai", "published_at": "2026-07-04 10:20:51+00:00", "updated_at": "2026-07-04 10:50:28.782619+00:00", "lang": "en", "topics": ["ai-tools", "artificial-intelligence", "computer-vision", "developer-tools"], "entities": ["AssistantAI", "Zoom", "Teams", "Telegram", "ScreenCaptureKit", "Silero VAD", "whisper.cpp", "OpenAI"], "alternates": {"html": "https://wpnews.pro/news/show-hn-assistantai-real-time-conversation-hints-and-screenshot-analysis", "markdown": "https://wpnews.pro/news/show-hn-assistantai-real-time-conversation-hints-and-screenshot-analysis.md", "text": "https://wpnews.pro/news/show-hn-assistantai-real-time-conversation-hints-and-screenshot-analysis.txt", "jsonld": "https://wpnews.pro/news/show-hn-assistantai-real-time-conversation-hints-and-screenshot-analysis.jsonld"}}