#94 · Primary category： Computer Vision
modlens
The first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding agent. Paste an image, get structured JSON evidence (OCR, layout, semantics).
Project last updated：08/27/26
GitHub Stars
3.8K
Forks
110
Contributors
1
License
MIT
Why we included this project
DeepSeek and GLM's flagship chat models are text-only, so they cannot read images on their own. ModLens plugs into a coding harness and gives that agent vision: paste an image into the chat and it returns structured JSON with the full transcription, reading-order layout, and entity/relation lists, so the model can quote what it actually sees instead of guessing. Setup is one skill folder on Claude Code, Codex, OpenCode, or Pi, plus one plugin on DeepSeek Harness, with no hooks, wrappers, or proxy daemon to maintain. It can also reuse vision engines you already have, from a free Gemini key to a signed-in Claude Code, chaining them with automatic failover. If your agents work with screenshots, diagrams, or documents, this is a practical way to get image input into an existing text-only pipeline.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
opencv
Open Source Computer Vision Library
RuView
π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.
PaddleOCR
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
MinerU
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
tesseract
Tesseract Open Source OCR Engine (main repository)