modlens — tool profile and history

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）。

Active

Canonical source ↗

Language
TypeScript
License
MIT
Created
Last activity
Topics
  • agent-skills
  • claude-code
  • claude-skills
  • codex
  • cordis
  • deepseek
  • dsh
  • dsh-plugin
  • glm
  • harness
  • harness-engineering
  • hermes-agent
  • image-to-text
  • multimodal
  • ocr
  • openclaw
  • pi-agent
  • text-only-llm
  • vision
  • vision-transformer

Install git clone https://github.com/liustack/modlens ~/.claude/skills/modlens

Current measurement

3 778GitHub stars+167 (+4.6 %)
measured growth

Momentum uses available readings from the last 7 days: measured with at least two comparable readings, estimated otherwise.

Reading history

90 days · 90 maximum readings
DateValueMetric
3 778GitHub stars
3 757GitHub stars
3 743GitHub stars
3 731GitHub stars
3 704GitHub stars
3 667GitHub stars
3 611GitHub stars
3 561GitHub stars
3 530GitHub stars
3 498GitHub stars
3 425GitHub stars
3 305GitHub stars
3 133GitHub stars
2 853GitHub stars
2 726GitHub stars
1 971GitHub stars
1 359GitHub stars
1 271GitHub stars

Classifications

Domains
Type
Agent skills
Use cases

These entries declare the same topics. No similarity is inferred: only the shared topics are stated.