liustack/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). | 全网最强 DeepSeek Harness 外挂视觉插件，为 DeepSeek、GLM 等纯文本模型外挂视觉能力，粘贴图片即得结构化 JSON 证据（OCR、版面、语义）。 observed · 2026-10-21
Health v2 · maintenance only
79/100
- Activity 100
- Release rhythm 87
- Longevity 17
How is this computed?
round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-10-21. Adoption (stars, forks) is never an input.
- gap_med: 0.0
- age_days: 240
- days_rel: 5
- days_push: 5
- n_releases_24m: 91
Adoption not part of the score
4365 stars · 133 forks observed · 2026-10-21
What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded
ModLens is a vision plugin for DeepSeek Harness (dsh) and other text-only coding agents that converts pasted images into structured JSON evidence including OCR, layout, and semantic analysis. It acts as a vision bridge, letting text-only models like DeepSeek and GLM read images directly from the chat.
Use cases
- give a text-only coding agent the ability to read pasted screenshots
- extract OCR text and layout from images as structured JSON
- let DeepSeek or GLM analyze UI mockups and diagrams
- add vision capabilities to a text-only LLM workflow
- read images pasted into chat without saving files first
- convert screenshots into semantic evidence for coding agents
When to choose
- you use DeepSeek, GLM, or another text-only model in a harness like dsh and need image understanding
- you want structured JSON output (OCR, layout, semantics) from images inside a coding agent
- you want zero-friction image input by pasting directly into chat
When to avoid
- your model already has native multimodal vision capabilities
- you need general-purpose standalone OCR outside an agent harness
- you don't use a supported harness such as DeepSeek Harness, Claude Code, or Codex
Facets
plugin · maturity active
ocr image-processing computer-vision agent-framework mcp artificial-intelligence image-processing developer-tools cli cross-platform vision-plugin deepseek-harness text-only-llm image-to- agent-skills claude-code multimodal-bridge ai-agents natural-language-processing nodejs
2 sources
- readme: https://github.com/liustack/modlens · fetched 2026-10-21 · a35f5bcd92e6
- homepage: https://liustack.dev · fetched 2026-08-29 · 79170bf4cd60
Member repositories
| Repository | Role | Health v2 |
|---|---|---|
| liustack/modlens | main | 79 |
For agents
markdown · JSON · MCP: product_card(name="liustack/modlens")
Data as of 2026-10-19T08:05:51.212177+00:00 · Report a problem