{"slug": "obs-agentic-control-interface", "title": "OBS Agentic Control Interface", "summary": "Antigravity, an agentic AI coding assistant, autonomously engineered a Rust-based agentic interface that allows users to control OBS Studio via natural language. The tool features a reasoning loop powered by Claude and OpenAI, real-time dashboard monitoring, and voice activation via the wake word \"OBSy\".", "body_md": "Note\n\n**🤖 100% Coded by AI**: This entire repository and application was engineered 100% autonomously by **Antigravity**, an agentic AI coding assistant.\n\nA powerful, self-contained agentic interface built in Rust that allows you to control OBS Studio via natural language. The system features an advanced reasoning loop powered by Claude (`claude-3-5-sonnet`\n\n) and OpenAI (`gpt-4o`\n\n), automatically connected to OBS Studio via WebSocket v5.\n\n**📊 Real-Time Interactive Dashboard**: Monitors streaming, recording, virtual camera, active program scenes, and audio mixer volume levels dynamically.**🖥️ Canvas Size & Output Resolution Detection**: Automatically queries your OBS Canvas and scaled output resolutions, displaying them in a dedicated status card and feeding them into the AI agent's system prompt context.**🧠 Intelligent Auto-Fallback Agent Loop**:- Routes requests through a robust agent loop with support for both Claude and OpenAI.\n**Dynamic failover**: If the selected provider key or network request fails, the backend automatically switches to the alternative provider (Claude ⇄ OpenAI) and finishes your request seamlessly without duplicating message history.\n\n**🔌 Windows Hotwire & WGC Binding**:- Remotely scans, restores, focuses, and resizes target application windows on your host OS.\n- Automatically binds windows into OBS using\n**Windows Graphics Capture (WGC / Windows 10 method)** to prevent black/grayed-out capture screens. - Uses an\n**intelligent fuzzy resolver** to match window titles/classes against OBS's active window pool to ensure 100% reliable binding.\n\n**🎙️ Real-Time Voice Activation (\"OBSy\")**:- Uses browser-side VAD (Voice Activity Detection) and OpenAI's Whisper API for high-fidelity speech-to-text.\n- Triggers on the wake word\n`\"OBSy\"`\n\n. Allows natural language control directly from your microphone.\n\n**🎛️ Manual Sidebar Controls**: Instant buttons to trigger scene changes, volume adjustments, and transitions that stay fully in sync with the AI's state.\n\n**OBS Studio**(v28.0 or later, featuring native WebSocket support).** Rust Toolchain**(pre-configured in this workspace environment).** GitHub CLI (**(for repository authentication and deployment).`gh`\n\n)\n\n- Open OBS Studio.\n- Navigate to\n**Tools**➔** WebSocket Server Settings**. - Check\n**Enable WebSocket server**. - Take note of the port (default:\n`4455`\n\n) and the password (or generate a new one).\n\nTo start the server, configure your credentials and connection endpoints as environment variables:\n\n```\n# Set your API keys (one or both are supported)\nexport ANTHROPIC_API_KEY=\"your-anthropic-api-key\"\nexport OPENAI_API_KEY=\"your-openai-api-key\"\nexport ELEVENLABS_API_KEY=\"your-elevenlabs-api-key\"\n\n# Set the connection host for OBS Studio\n# When running inside a container, set to \"host.docker.internal\" to connect to the host\nexport OBS_HOST=\"host.docker.internal\"\nexport OBS_PORT=\"4455\"\nexport OBS_PASSWORD=\"your-obs-websocket-password\"\n```\n\nTo compile and launch the Axum web server, run the following in the workspace directory:\n\n```\ncargo run\n```\n\nThe server will initialize and serve the frontend dashboard at `http://localhost:8080`\n\n.\n\nOpen your browser, connect OBS, and start commanding your streams via text or voice!", "url": "https://wpnews.pro/news/obs-agentic-control-interface", "canonical_source": "https://github.com/DeepBlueDynamics/obsagent", "published_at": "2026-06-17 00:08:41+00:00", "updated_at": "2026-06-17 00:22:18.344667+00:00", "lang": "en", "topics": ["ai-agents", "ai-tools", "large-language-models", "natural-language-processing", "developer-tools"], "entities": ["Antigravity", "OBS Studio", "Claude", "OpenAI", "Whisper", "ElevenLabs", "GitHub", "Rust"], "alternates": {"html": "https://wpnews.pro/news/obs-agentic-control-interface", "markdown": "https://wpnews.pro/news/obs-agentic-control-interface.md", "text": "https://wpnews.pro/news/obs-agentic-control-interface.txt", "jsonld": "https://wpnews.pro/news/obs-agentic-control-interface.jsonld"}}