🏆 #1,788 overall#273 of 313 in OCR & Documents

oxbshw /watch-skill

Give AI agents eyes, ears, and verifiable results. Watch Skill turns video, audio and screen activity into searchable, timestamped evidence and proves work with deterministic contracts, not model opinion. DeepWatch is the agent workspace built on DeepSeek Harness. Python + npm, MCP, CLI, REST, Web.

$ git clone https://github.com/oxbshw/watch-skill.git
GitHub social preview for oxbshw/watch-skill
Stars
390
390
Forks
56
56
Language
Python
License
MIT
Created
Jul 5, 2026
0.2 years old
Last push
Sep 14, 2026

Categories

GitHub topics

More in OCR & Documents

OCR & Documents

Anionex/dsh-vision-toolkit

[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.

TypeScriptMITupdated Sep 16, 2026
GitHub ↗★ 884⑂ 47
OCR & Documents

Zipstack/unstract🔥 active

LLM-Driven Extraction of Unstructured Data — Built for API Deployments & ETL Pipeline Workflows

PythonAGPL-3.0updated Sep 24, 2026
GitHub ↗★ 7.3K⑂ 720
OCR & Documents

liustack/modlens🔥 active

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)。

TypeScriptMITupdated Sep 24, 2026
GitHub ↗★ 4K⑂ 123
OCR & Documents

garylab/MakeMoneyWithAI🔥 active

A list of open-source AI projects you can use to generate income easily.

🧠 Natural Language Processing
Pythonno licenseupdated Sep 24, 2026
GitHub ↗★ 948⑂ 148
OCR & Documents

neosun100/DeepSeek-OCR-WebUI

🎨 Ready-to-use DeepSeek-OCR Web UI | Modern Interface | 7 Recognition Modes | Batch Processing | Real-time Logging | Fully Responsive

TypeScriptMITupdated Feb 20, 2026
GitHub ↗★ 447⑂ 95

Data from GitHub · snapshot Sep 24, 2026