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）。
Build with Backblaze B2
SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.
Loading star history...
Where it stands
Rank, growth pace and release cadence relative to everything GStars tracks.
5 releases in the last 90 days, the latest 10 days ago, with 1 contributor on GitHub.
Use Cases & Benefits
- Provides a vision plugin that enables text-only AI models to interpret pasted images and return structured JSON with OCR, layout, and semantic data.
- Integrates seamlessly with multiple AI harnesses without config changes, reusing existing vision engines or free APIs for fast, zero-setup image understanding.
- Use for adding image-reading capabilities to text-only chat models like DeepSeek, GLM, or Claude Code without modifying their core code.
- Use for extracting detailed structured evidence from screenshots, charts, or documents pasted directly into AI chat interfaces for analysis or automation.
- Use for building multimodal AI agents that combine text and visual inputs by bridging image content into text-based workflows with minimal overhead.
Should you depend on it?
License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.
License
MIT
Permissive: commercial use, modification and redistribution are allowed with attribution.
Community files
- README: present
- Contributing guide: present
- Code of conduct: present
Watch-outs
- Owned by an individual account with a single contributor on GitHub; plan for bus-factor risk.
General guidance from repository metadata, not legal advice. How we score
From the README
Give a text-only model sight, and just paste the image.
🥇 The FIRST vision plugin for DeepSeek Harness (dsh) 🥇
The flagship DeepSeek and GLM chat models are text-only and cannot read images. ModLens is a plug-in vision engine that gives a text-only model sight. ModLens reads images pasted straight into the chat, no saving to a file and passing a path first.
Issues are welcome any time: open one. And come find me on X: @liustack. What you built with it, which harness you are on, what should come next. New releases land there first, and a proper community space is on the way.
🥇 The first vision plugin for DeepSeek Harness (dsh): one command,
npx -y @deepseek-ai/dsh plugin --profile web add @liustack/[email protected], and the text-only DeepSeek model behind dsh reads images through a nativemodlens_read_imagetool. Updating is the same command again. The version is named rather than@lateston purpose: pnpm 11 holds back releases published in the last 24 hours and resolves the tag against what survives, so@latestwould install whatever shipped a day ago (details).
Daily snapshots
Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots
+2,861 stars over 80 days across 9 snapshot days; best day +573 on Aug 17.
Forks
148+100
Open issues
3-3
Compared with peers in Computer Vision
Fastest-growing repositories GStars tracks in this cohort for the week of Nov 1, by 7-day star growth
| Repository | Stars | +7d | Health | Last release |
|---|---|---|---|---|
| mudler/LocalAI | 50.2K | +176 | 59 | 12 days ago |
| PaddlePaddle/PaddleOCR | 92.3K | — | 47 | 147 days ago |
| d2l-ai/d2l-en | 30.0K | — | 45 | — |
| lukas-blecher/LaTeX-OCR | 16.6K | — | 18 | — |
| liustack/modlens | 4.7K | — | 37 | 10 days ago |
| SharpAI/DeepCamera | 3.1K | — | 31 | 227 days ago |
| Category median | 30.0K | — | 45 | — |
Discover Repositories
Search across tracked repositories by name or description