chriswritescode-dev/opencode-eyesight

give non-vision models the ability to see images by routing images to a vision capable model

Near-native image understanding for DeepSeek Harness

Give text-only LLMs vision. A tiny OpenAI-compatible proxy that lets reasoning models (DeepSeek, Qwen, GLM…) see images by querying a separate vision model through tools: look, OCR, scan, crop, compare. No training, no weights.

CLIProxyAPI v7 plugin for DeepSeek Responses vision preprocessing

Give text based LLMs in Claude Code working eyes using a local Ollama vision model. Screen capture, clipboard reading, and image file analysis — no cloud, no uploads, 100% local.

VisionPower: portable image understanding MCP server for Codex, Claude Desktop, Cursor, and other agents.

`pi-deepseek-vision` is a vision preprocessing extension for Pi 0.84.1. It uses a vision model already available in Pi to analyze images in the current visible context, replaces them with numbered markers and plain-text analysis, and then calls the target DeepSeek model. The DeepSeek model itself always remains text-only.

The vision plugin for OpenCode that truly understands images. Inspect, read, and reason about any screenshot or picture with deeper understanding than any other plugin — fully local, private, and free.

ds-vision-skill: Vision skill suite to add multimodal image capabilities for DeepSeek, and other text-only models as well.