Footer

Your go-to destination for discovering trending open-source projects and uncovering the insights that matter

Legal

  • Terms and conditions
  • Privacy policy

More

  • Pricing
  • Advertise
  • onedump
  • gosnakego
  • Contact us

Social

  • X (Twitter)
  • GitHub
Trendshift owl
What they build speaks louder than words
© 2026 Trendshift, created by Julian Li with ❤️
SignalAdvertise
Trendshift
SignalAdvertise
Sign in
Trendshift owl

Discover trends that matter

SignalAdvertise
DailyWeeklyMonthlyYearly
Live mentionsTopics
RepositoriesDevelopers
InsightsStats
Bifrost
Bifrost
Busbar
Busbar
Omnigraph
Omnigraph
Websitebench
Websitebench

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）。

Visit GitHub
TypeScript
4.9k
163
2 contributors
MIT License
website
AchievementsView all →
FeaturedAdvertise to 180K+ monthly visitors
Bifrost

Fastest Enterprise AI Gateway for Routing, Governing, and Securing all your AI Traffic

Busbar

Control what AI can do before it acts

Omnigraph

Versioned graph database on object storage. Git-style workflows and multimodal retrieval

Websitebench

Can AI agents reverse-engineer real websites?

Momentum

How fast liustack/modlens is gaining stars, and where it lands on Trendshift and GitHub Trending

Activity and trending

Stars, forks and merged pull requests each day or month, lined up with the repository's rank on Trendshift Trending

Sep 11 – Nov 10, 2026

Stars +956 in 61 days

0204060
51

Forks +39 in 61 days

024
4

Merged PRs 0 in 61 days

01

Trendshift Trendingwhere the repository ranked each day it made the top 25

Not in the Trendshift top 25 in this period

Sep 11Sep 19Sep 27Oct 5Oct 13Oct 21Oct 29Nov 6
The left and right arrow keys step from day to day; Home and End go to the first and the last

Stars, forks, merged pull requests and Trendshift Trending rank, by day
DayStars gainedForks gainedMerged PRs
Fri, Sep 11, 2026+10+00
Sat, Sep 12, 2026+7+10
Sun, Sep 13, 2026+7+10
Mon, Sep 14, 2026+0+00
Tue, Sep 15, 2026+8+00
Wed, Sep 16, 2026+7+00
Thu, Sep 17, 2026+5+10
Fri, Sep 18, 2026+6+00
Sat, Sep 19, 2026+9+10
Sun, Sep 20, 2026+5+20
Mon, Sep 21, 2026+4+00
Tue, Sep 22, 2026+13+00
Wed, Sep 23, 2026+3+00
Thu, Sep 24, 2026+7+00
Fri, Sep 25, 2026+11+10
Sat, Sep 26, 2026+8+00
Sun, Sep 27, 2026+6+00
Mon, Sep 28, 2026+9+00
Tue, Sep 29, 2026+12+10
Wed, Sep 30, 2026+19+00
Thu, Oct 1, 2026+8+20
Fri, Oct 2, 2026+4+10
Sat, Oct 3, 2026+6+00
Sun, Oct 4, 2026+10+10
Mon, Oct 5, 2026+2+10
Tue, Oct 6, 2026+17+00
Wed, Oct 7, 2026+13+10
Thu, Oct 8, 2026+14+00
Fri, Oct 9, 2026+13+00
Sat, Oct 10, 2026+13+00
Sun, Oct 11, 2026+17+00
Mon, Oct 12, 2026+16+10
Tue, Oct 13, 2026+12+00
Wed, Oct 14, 2026+21+00
Thu, Oct 15, 2026+13+10
Fri, Oct 16, 2026+16+00
Sat, Oct 17, 2026+12+10
Sun, Oct 18, 2026+12+10
Mon, Oct 19, 2026+28+10
Tue, Oct 20, 2026+23+00
Wed, Oct 21, 2026+23+00
Thu, Oct 22, 2026+24+10
Fri, Oct 23, 2026+21+20
Sat, Oct 24, 2026+13+00
Sun, Oct 25, 2026+17+10
Mon, Oct 26, 2026+31+10
Tue, Oct 27, 2026+45+10
Wed, Oct 28, 2026+51+10
Thu, Oct 29, 2026+44+10
Fri, Oct 30, 2026+20+20
Sat, Oct 31, 2026+32+40
Sun, Nov 1, 2026+20+00
Mon, Nov 2, 2026+22+10
Tue, Nov 3, 2026+14+10
Wed, Nov 4, 2026+26+10
Thu, Nov 5, 2026+18+10
Fri, Nov 6, 2026+32+10
Sat, Nov 7, 2026+25+10
Sun, Nov 8, 2026+19+00
Mon, Nov 9, 2026+20+00
Tue, Nov 10, 2026+13+00
Total+956+390
  • 1#1 on the list
  • 7Rank that day
  • Not trending
4

    • GitHub trending history

    Where the repository ranked on GitHub Trending, one dot for each day it was on a list

    TypeScript

    Aug 15 – Aug 17, 2026Best #4

    #1#5#10#15#20#25
    Top 10
    Aug 15, 2026Aug 17, 2026
    The left and right arrow keys step from day to day; Home and End go to the first and the last

    Mentions and achievements

    Where people are talking about liustack/modlens, and every badge it has earned
    1. Nov 71 post

      • DeepSeek Harness (DSH) 的开源生态最近彻底爆发了！🐋🔥 如果你还在裸奔用原版 DSH，那真的错过了太多神仙体验。我花时间盘点了目前 GitHub 上最受欢迎、Star 最高的 10 个 DSH 必装神级插件，从可视化市场、全能工作台、终端 UI 到视觉外挂、跨平台记忆和多智能体协作，直接把你的 DSH 武装到牙齿！ 建议先马后看 👇

        Read full on X, posted by @Cryptoxorz

        @Cryptoxorz · x.com

    2. Nov 41 post

      • 8,600+ DSH plugins exist. here's what people actually install (npm, 30d): billion-context 2.8M dsh-market 920k dsh-web suite 694k dsh-pet 416k whale-widget 398k dsh-context 345k better-sidebar 265k…

        Read full on X, posted by @seanhighness

        @seanhighness · x.com

    3. 2 months earlier
    4. Aug 261 post

      • DeepSeek Harness 最近的生态爆发速度有点夸张， 盘了一下 2026 年 8 月社区评分最高的 TOP 10 必备插件，体验直接拉满了！ 玩 DeepSeek Harness 的朋友如果还在用默认毛坯界面，建议把这 10 个插件装上， 社区实测横评前 10 名，直接把一个命令行黑框武装成了完全体工作台 对照榜单梳理了一下核心价值，建议按需对号入座: 🏆 01.…

        Read full on X, posted by @AYi_AInotes

        @AYi_AInotes · x.com

    5. Aug 221 post

      • 刚跑了一个今天约 3.5k Star 的 GitHub 项目 ModLens。它想做的事很直接：给纯文本 DeepSeek、GLM 补上读图能力。 结果比“神器推荐”更有意思。 项目能正常构建，doctor 也把本机 Antigravity CLI 判定为 ready。真正拿仓库自带的公开图片做端到端测试时，却直接失败：ModLens 传入 `--output-format`，而本机…

        Read full on X, posted by @thelazyyogii

        @thelazyyogii · x.com

    6. 8 days earlier
    7. Aug 141 post

      • 梁圣的 DeepSeek 重磅发布 Harness： 最大特色：一切皆插件！ 开发者不需要改源码，只通过配置就能组合AI能力，现在社区插件排名： 1. colleague-skill 同事 Skill 将冰冷的离别化为温暖的 Skill。提供飞书/钉钉/Slack 消息、文档、邮件、截图 + 主观描述，生成真正能替该同事工作的 AI Skill，支持数字生命传承。 2. iPolloWork…

        Read full on X, posted by @web3annie

        @web3annie · x.com

    8. Aug 81 post

      • After cancelling $200/mo Claude plan I replaced Opus 5 with Deepseek V4 Flash at 1/20th price one problem: it can't see. no images, no video then i found a 2-package trick that gives vision onto any…

        Read full on X, posted by @Av1dlive

        @Av1dlive · x.com

    9. Aug 64 posts

      • Engineered to upgrade existing AI workflows with minimal compute overhead: • Bridge the Gap: Allows legacy or highly specialized text models to process visual inputs seamlessly. • Cost-Effective…

        Read full on X, posted by @TheTechDiggest

        @TheTechDiggest · x.com

      • إذا كنت تستخدم نماذج ذكاء اصطناعي لا تدعم قراءة الصور، فهذا المشروع يستحق الاطلاع. ModLens يحول أي صورة إلى بيانات منظمة (OCR، تخطيط الصفحة، والعناصر داخلها)، بحيث يستطيع النموذج النصي فهمها والإجابة…

        Read full on X, posted by @Sn0wbrave

        @Sn0wbrave · x.com

      • 推荐两个Pi Agent好用的插件 让你的deepseek具备生图和识图功能 用GPT生图： 识图:

        Read full on X, posted by @zhang_baoqing

        @zhang_baoqing · x.com

      • 推荐连个Pi Agent好用的插件 让你的deepseek具备生图和识图功能 用GPT生图： 识图:

        Read full on X, posted by @zhang_baoqing

        @zhang_baoqing · x.com

    You might also like

    Repositories close to liustack/modlens
    FeaturedAdvertise to 180K+ monthly visitors
    Websitebench

    Can AI agents reverse-engineer real websites?

    Busbar

    Control what AI can do before it acts

    Omnigraph

    Versioned graph database on object storage. Git-style workflows and multimodal retrieval

    Bifrost

    Fastest Enterprise AI Gateway for Routing, Governing, and Securing all your AI Traffic

    Sorwcyra/ds-vision-skill

    PowerShell

    ds-vision-skill: Vision skill suite to add multimodal image capabilities for DeepSeek, and other text-only models as well.

    15811

    itsmeadarsh2008/opencode-senses

    TypeScript

    The vision plugin for OpenCode that truly understands images. Inspect, read, and reason about any screenshot or picture with deeper understanding than any other plugin — fully local, private, and free.

    933

    ysr666/dsh-vision-router

    JavaScript

    Eyes for text-only DeepSeek Harness agents: built-in free vision chain (no key) + pixel-level vision tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots). One-command install, no Python, image turns work like ordinary tool-calling turns.

    1.3k71

    thomasunise/visionbridge

    Python

    Give text-only LLMs vision. A tiny OpenAI-compatible proxy that lets reasoning models (DeepSeek, Qwen, GLM…) see images by querying a separate vision model through tools: look, OCR, scan, crop, compare. No training, no weights.

    492

    landing-ai/vision-agent

    Python

    This tool has been deprecated. Use Agentic Document Extraction instead.

    5.3k611

    Anionex/dsh-vision-toolkit

    TypeScript

    [dsh]为纯文本模型设计更强大的视觉工具箱：一行安装使用、粘贴图片直接识别、多张图片问答、截图到前端UI 还原等｜DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, long-screenshot OCR, UI restoration, grounding, pixel diff, Artifacts, and Web UI.

    93757

    NoPainNullGain/LocalEyes

    Python

    Give text based LLMs in Claude Code working eyes using a local Ollama vision model. Screen capture, clipboard reading, and image file analysis — no cloud, no uploads, 100% local.

    281

    deepseek-ai/DeepSeek-OCR-2

    Python

    Visual Causal Flow

    3.5k340

    RunhuaHuang/VisionPower

    JavaScript

    VisionPower: portable image understanding MCP server for Codex, Claude Desktop, Cursor, and other agents.

    688