Trending repositories: multi-modal

4 of 4 repositories

• agentscope-ai/agentscope

  Build and run agents you can see, understand and trust.

  AI summary: A developer-centric multi-agent platform with built-in fault tolerance and drag-and-drop orchestration.

  28,691ai-mlPythonApache-2.0agentchatbotlarge-language-modelsllm

• bradautomates/claude-video

  Give Claude the ability to watch any video. /watch downloads, extracts frames, transcribes, hands it all to Claude.

  AI summary: A plugin granting Claude the ability to securely download, transcribe, and analyze video content.

  14,399ai-mlPythonMITclaude-pluginvideo-analysistranscriptionmulti-modal

• GetStream/Vision-Agents

  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 summary: Multi-modal AI agents by Stream for real-time video understanding with sub-30ms latency.

  8,006ai-mlPythonApache-2.0agentic-aiagentsaiai-agents

• Emily2040/seedance-2.0

  Comprehensive production pipeline for quad-modal AI filmmaking with Seedance 2.0

  AI summary: Comprehensive production pipeline for quad-modal AI filmmaking with Seedance 2.0.

  6,201ai-mlPythonMITai-filmmakingmulti-modalvideo-generationagent-skills