dsh-see-now

让 AI 实时看见你的屏幕:按变化量筛选帧、多帧拼进一张图,静止画面几乎不花 token

SAOS-3624/dsh-see-now

View on GitHub ↗

让 AI 实时看见你的屏幕:按变化量筛选帧、多帧拼进一张图,静止画面几乎不花 token

dsh-see-now ranks 75th of 341 in Voice / Vision I/O, actively maintained, last commit today.

Star trajectory

18 days tracked
2026-11-04731 stars today2026-11-22
Momentum

- in 30d, below the Voice / Vision I/O median of +5.0%.

Maintenance

Last commit today, fresher than the median of 6d.

How it compares in Voice / Vision I/O

dsh-see-now
731
stars
- 30d
commit today
Voice / Vision I/O median
217
stars
+5.0% 30d
commit ~6d ago
Leader · mcp-for-blender
35.3k
stars
+10.1% 30d
commit 3 days ago

Ranked 75th of 341 by stars.

Ranked by shared tags, then keywords, then stars
  1. Durable AI agents for Apple platforms: pi-durable on JavaScriptCore with a Swift API

    +26 (+9.4%) in 30d · Committed 21d ago · Swift · CC0-1.0

    Shares Tools & Integrations, Voice / Vision I/O

  2. Community plugin to control Blender 3D with any LLM of your choice. Not affiliated with the official Blender…

    +3.2k (+10%) in 30d · Committed 3d ago · Python · MIT

    Shares Tools & Integrations, Voice / Vision I/O

  3. Build your own AI office with Univer Office SDK. Bring editing, calculation, collaboration, and file…

    +8.4k (+37%) in 30d · Committed today · TypeScript · Apache-2.0

    Shares Tools & Integrations, Voice / Vision I/O

  4. The fastest browser for AI agents to run browser automation, built for sharing your logged-in browser state…

    +5.1k (+27%) in 30d · Committed today · JavaScript · MIT

    Shares Voice / Vision I/O, Tools & Integrations

  5. Let Claude (or any LLM) actually watch a video — scene-aware, deduplicated frames + transcript, from a URL or…

    +77 (+3.4%) in 30d · Committed 2d ago · Python · MIT

    Shares Tools & Integrations, Voice / Vision I/O

  6. Eyes for text-only DeepSeek Harness agents: built-in free vision chain (no key) + pixel-level vision tools…

    +130 (+11%) in 30d · Committed yesterday · JavaScript · MIT

    Shares Tools & Integrations, Voice / Vision I/O

  7. 为纯文本模型"看图“设计更好的视觉工具箱和技能,支持多图理解,图片问答,前端UI还原、GUI 自动化等,并可选无缝接入多个主流agent,直接识别粘贴图片| A vision toolkit and skill…

    +19 (+1.5%) in 30d · Committed 39d ago · Python · MIT

    Shares Tools & Integrations, Voice / Vision I/O

  8. Temporary rooms for Humans and AI Agents — run, supervise and steer Agent Tasks without a permanent workspace.

    +11 (+0.9%) in 30d · Committed 5d ago · TypeScript · MIT

    Shares Voice / Vision I/O, Tools & Integrations

  9. 提供产品级IOCR自定义模板识别,以图搜图,人像搜索等,免费,可商用,Java AI 人工智能一站式解决方案,为工作减负,为产品研发加速。项目类别包括:以及AI SDK,web应用等。

    -1 (-0.1%) in 30d · Committed 200d ago · Java · Apache-2.0

    Shares Tools & Integrations, Voice / Vision I/O

  10. [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…

    +45 (+5.0%) in 30d · Committed today · TypeScript · MIT

    Shares Tools & Integrations, Voice / Vision I/O

Language
JavaScript
License
Apache License 2.0
Contributors
13
Forks
74
Watchers
1
Open issues
2
Releases
16
Created
2026-11-01
Stars this week
+82

You've seen where dsh-see-now stands today.

Get the moves before everyone else: the 5 Voice / Vision I/O repos climbing fastest, every Tuesday.

Free weekly digest. Double opt-in, unsubscribe anytime.

Maintain dsh-see-now?

Claim this page to add your own call-to-action.

Claim this page