Pi extension: describes images with a configured vision model when the active model cannot see

DSH vision/image-recognition plugin: enables AI to understand images with a configurable vision model

AI SDK (Vercel) provider for Mixlayer — open-weight text and vision model inference over an OpenAI-compatible endpoint.

Transparent image-to-text bridge for text-only Pi models using a configurable vision model

Registers a describe_image tool that routes image analysis to a configured vision model through pi's official pipeline.

Give text-only pi models vision — describe images with a vision model you pick via an interactive picker, then hand off the text description to non-vision models

Model-facing accurate_vision tool: precise image spatial reasoning via a vision model

MCP stdio server for image recognition via an existing vision model

The image_inspect tool: the main model hands one picture and one question to a vision model and gets an answer back

Lightweight, route-preserving vision link for DSH: a configured vision model sees while the selected text model stays in control.

OpenCode plugin: vision_analyze tool — describe images & image URLs with your own vision model for text-only main models; native-image fast path for multimodal models. Zero runtime dependencies.

Capability-aware vision + paste extension for the pi coding agent. Delegates image analysis to a vision model only when the active primary model is text-only; passes images through natively for multimodal models (zero delegation).

Describe images with a vision model so text-only DeepSeek Harness models can read them

Give text-only pi models vision — describe images with a vision model you pick via an interactive picker, then hand off the text description to non-vision models

Route pasted images to a cheap vision model in opencode so text-only main agents work from its text output.

LLM-native image optimization MCP server. Reduces vision model token consumption by snapping to tile boundaries.

argus-reviewer — open-source vision-model E2E testing harness. Record, replay, heal, and assert with any OpenRouter model under a hard budget cap.

Real mouse and keyboard for a DeepSeek Harness agent: describe what to click in words, a vision model finds it, a USB HID device clicks it.

MCP server for Alibaba Qwen3.7-plus vision model via DashScope Anthropic-compatible API

On-demand vision for text-only DSH sessions: images become markers, and a vision_describe tool sends only image + question to an OpenAI-compatible vision model