Visual-Agent/DeepEyesV2

Agentic multimodal model with code execution and web search

View on index · View in 3D Map

Related repos

• Visual feedback tool for AI coding agents
• Analyzes AI agent coding sessions in a web interface
• multimodal agent with long-term memory for real-time visual and audio reasoning
• Local AI agent for web browsing and coding
• Benchmark for multimodal agents in data engineering workflows
• Real-time multimodal AI agent framework
• Foundation model for multimodal agents
• Builds real-time vision AI agents
• vision-based agent automates browser tasks like a human
• AI agent framework for complex task automation