OCR & Documents
emcf/thepipe
Get clean data from tricky documents, powered by vision-language models ⚡
🤖 Language Models
PythonMITupdated Sep 28, 2026
🏆 #6,597 overall#650 of 693 in OCR & Documents🔥 active this week
oidlabs-com /Lexoid
The open-source universal adapter for LLMs. Turn messy real-world data into clean, agent-ready context.
$ git clone https://github.com/oidlabs-com/Lexoid.gitStars
109
109
This week
—
Forks
15
15
Language
Python
License
Apache-2.0
Created
Sep 22, 2024
2.1 years old
Last push
Nov 12, 2026
🔥 this week
Categories
More in OCR & Documents
OCR & Documents
hiroi-sora/Umi-OCR
▲ +157 ★ this week
OCR software, free and offline. 开源、免费的离线OCR软件。支持截屏/批量导入图片，PDF文档识别，排除水印/页眉页脚，扫描/生成二维码。内置多国语言库。
PythonMITupdated Nov 20, 2025
OCR & Documents
adithya-s-k/omniparse
▲ +1 ★ this week
Ingest, parse, and optimize any data format ➡️ from documents to multimedia ➡️ for enhanced compatibility with GenAI frameworks
PythonGPL-3.0updated Dec 12, 2025
OCR & Documents
Sumanth077/Hands-On-AI-Engineering🔥 active
▲ +17 ★ this week
A curated collection of practical AI projects implementing OCR systems, RAG, AI agents, and other AI use cases.
🔍 Search & Retrieval
Pythonno licenseupdated Nov 7, 2026
OCR & Documents
CatchTheTornado/text-extract-api
▲ +11 ★ this week
Document (PDF, Word, PPTX ...) extraction and parse API using state of the art modern OCRs + Ollama supported models. Anonymize documents. Remove PII. Convert any document or picture to structured JSON or Markdown
PythonMITupdated Dec 8, 2025
OCR & Documents
HUANGCHIHHUNGLeo/claude-real-video
▲ +20 ★ this week
Let Claude (or any LLM) actually watch a video — scene-aware, deduplicated frames + transcript, from a URL or local file. Runs locally, MIT.
PythonMITupdated Oct 23, 2026
Data from GitHub · snapshot Nov 13, 2026