Skip to content

v1.1.0

Choose a tag to compare

@code-yeongyu code-yeongyu released this 13 Dec 06:29
· 226 commits to dev since this release

New Features

🔍 look_at Tool & multimodal-looker Agent

  • Add look_at tool for analyzing media files (PDFs, images, diagrams)
  • Add multimodal-looker agent using Gemini 2.5 Flash model
  • Analyze visual content in separate context window, saving main conversation tokens

Inspired by Sourcegraph Ampcode's look_at tool design.

Usage

look_at({
  file_path: "/path/to/diagram.png",
  goal: "Describe the architecture components"
})

Supported File Types

  • PDF documents
  • Images (PNG, JPG)
  • Screenshots
  • Architecture diagrams
  • Charts/Graphs