Plugin: a0_vision_fallback

[a0-bot[bot]]

Vision Fallback

Routes image analysis to a dedicated vision model when the main chat model doesn't support vision. Intercepts images before they reach the LLM, sends them to a configurable vision model (via LiteLLM), and replaces the image with a text description. Works with any text-only model like glm-5.2, deepseek, or llama3. Features auto API key detection from .env, hash-based cache, and dark mode UI.

Quick links

• Index entry: https://github.com/agent0ai/a0-plugins/tree/main/plugins/a0_vision_fallback
• Plugin repository: https://github.com/lelabdev/a0-vision-fallback
• Author: @lelabdev

About this discussion

This discussion is auto-created by a workflow when a plugin is added to the index.