OCR & Documents
yigitkonur/api-llm-ocr
▲ +1 ★ this week
PDF to markdown using vision LLMs — tables, layouts, and structure preserved
PythonOtherupdated Feb 21, 2026
🏆 #5,603 overall#553 of 693 in OCR & Documents
CHEN010325 /paddleocr-local
Local-first document parsing workbench for five OCR models: PDF/Office to Markdown with WebUI, model switching, CLI and Apple Silicon support.
$ git clone https://github.com/CHEN010325/paddleocr-local.gitStars
142
142
This week
—
Forks
33
33
Language
Python
License
Apache-2.0
Created
Feb 23, 2026
0.7 years old
Last push
Nov 1, 2026
Categories
More in OCR & Documents
OCR & Documents
velviagris/PaddleOCRFastAPI
A simple way to deploy PaddleOCR based on FastAPI. (PaddleOCR 的 FastAPI 快速部署方案)
PythonMITupdated Oct 8, 2025
OCR & Documents
xerrors/Yuxi🔥 active
可私有部署的多租户知识智能体平台：统一 RAG、知识图谱、多智能体、MCP/Skills、沙盒与权限管理。Yuxi = Cloud Agents + Knowledge RAG, Self-hosted knowledge agent platform for RAG, knowledge graphs and multi-agent workflows.
🔍 Search & Retrieval
PythonMITupdated Nov 13, 2026
OCR & Documents
aiptimizer/TurboOCR
▲ +3 ★ this week
TurboOCR, >200 img/s OmnidocBench. TensorRT FP16, PP-OCRv6, HTTP + gRPC
🔍 Search & Retrieval
C++MITupdated Sep 27, 2026
OCR & Documents
magicrew/doc7
Turn documents into AI-ready Markdown with visual understanding
GoMITupdated Aug 7, 2026
OCR & Documents
vorojar/Folio-OCR
▲ +3 ★ this week
Open-source batch OCR workbench — a free, local alternative to ABBYY FineReader. Powered by Ollama + GLM-OCR + PP-DocLayoutV3, ~0.5s/page on RTX 4090. Three-panel editor, layout-aware, PDF/image batch processing, Markdown/Word export. 批量OCR工作台，纯本地运行，免费平替ABBYY，适合书籍文档数字化。
PythonMITupdated Jun 18, 2026
Data from GitHub · snapshot Nov 13, 2026