aiptimizer/TurboOCR

TurboOCR, >200 img/s OmnidocBench. TensorRT FP16, PP-OCRv6, HTTP + gRPC

document-aidocument-parsingeasyocrfastapifp16gpu-ocrgrpcinference-servernvidiaocr

License & maintenance

MIT is a permissive license: free to use commercially with attribution.

Last code push 22 days ago.

	Repository	Stars	Language	License	Activity
1	PaddlePaddle/PaddleOCRTurn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDF	★ 91.3k	Python	Apache-2.0	Active
2	opendataloader-project/opendataloader-pdfPDF Parser for AI-ready data. Automate PDF accessibility. Open-source.	★ 29.7k	Java	Apache-2.0	Active
3	headroomlabs-ai/headroomCompress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JS	★ 75.8k	Python	Apache-2.0	Active
4	paperless-ngx/paperless-ngxA community-supported supercharged document management system: scan, index and archive all your documents	★ 46.8k	Python	GPL-3.0	Active
5	go-kratos/kratosYour ultimate Go microservices framework for the cloud-native era.	★ 26k	Go	MIT	Active
6	jundot/omlxLLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar	★ 22.9k	Python	Apache-2.0	Active
7	NVIDIA/NemoClawRun agents like Hermes, LangChain Deep Agents, and OpenClaw more securely inside NVIDIA OpenShell with managed inference	★ 22.8k	TypeScript	Apache-2.0	Active
8	microsoft/unilmLarge-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities	★ 22.2k	Python	MIT	Active