vision-ai

Open Vision Agents by Stream. Build voice and vision agents quickly with any model or video provider. Uses Stream's edge network for ultra-low latency.

AI-powered companion for Homebox. Snap photos and let AI auto-identify and catalog items into your inventory, then use the AI Chat to organize, search, and update your inventory effortlessly.

Open-source implementation of Pomelli project by Google

🐊 Snappy's unique approach unifies vision-language late interaction with structured OCR for region-level knowledge retrieval. Like the project? Drop a star! ⭐

Smart multi-agent conversational assistant with LangGraph orchestration, Human-in-the-Loop, enterprise-grade observability, and full i18n support (6 languages)

Gemini Vision & Image Generation MCP for Claude Desktop and Claude Code