Repository · GitHub

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）。

View on GitHubReport an issue

Owner	liustack
License (as declared)	MIT
Stars	4,411
Forks	135
Main language	TypeScript
Created	22 February 2026
Last updated at source	15 October 2026

typescriptagent-skillsclaude-codeclaude-skillscodexcordisdeepseekdshdsh-pluginglmharnessharness-engineeringhermes-agentimage-to-textmultimodalocropenclawpi-agenttext-only-llmvisionvision-transformer

Embed this entry

<iframe src="https://silytics.si/embed/item/cb5b3af3-cb3f-4576-bbf1-26fc4eb778b1" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Free, no tracking. More about feeds and embeds.

Stars, last 8 days

4,411 now (+139 since 2026-10-16). Counts as reported by the source, snapshotted daily by Silytics.

More from liustack

@liustack/modsearchRepository

Silytics shows public metadata from GitHub and links to the original. Information may be incomplete or out of date. Last refreshed 23 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.