#ocr Repositories
255 repositories total
LLM Agent Framework in ComfyUI includes MCP sever, Omost,GPT-sovits, ChatTTS,GOT-OCR2.0, and FLUX prompt nodes,access to Feishu,discord,and adapts to all llms with similar openai / aisuite interfaces, such as o1,ollama, gemini, grok, qwen, GLM, deepseek, kimi,doubao. Adapted to local llms, vlm, gguf such as llama-3.3 Janus-Pro, Linkage graphRAG
Assist in organizing your piles of documents, resulting from scanners, e-mails and other sources with miminal effort.
AALC, Limbus Company Assistant on PC. AALC, Limbus Company Assistant on PC.
A tool to convert a wallpaper's color scheme/palette, perform OCR using VLM's Traditional & Hybrid methods, handle image compression, color palette extraction, image upscaling with Adversarial Networks, and offer more image processing features.
Let Claude (or any LLM) actually watch a video โ scene-aware, deduplicated frames + transcript, from a URL or local file. Runs locally, MIT.
Rust multiโbackend OCR/VLM engine (DeepSeekโOCR-1/2, PaddleOCRโVL, DotsOCR) with DSQ quantization and an OpenAIโcompatible server & CLI โ run locally without Python.
Browser and desktop automation with an MCP server for AI assistants. Record macros or write JavaScript to automate websites, extract data, and control desktop apps with OCR and image recognition.
An on-premises, OCR-free unstructured data extraction, markdown conversion and benchmarking toolkit. (https://idp-leaderboard.org/)
QuickClipboard is a cross-platform clipboard enhancement tool (currently supporting Windows and Android), built with Tauri 2 + Rust + React. It starts working the moment you copyโautomatically recording text, images, rich text, and files, allowing you to retrieve anything you've copied at any time. Beyond just recording, QuickClipboard integrates features like image pinning, OCR, and LAN synchronization, providing a comprehensive boost to your daily office productivity.
1M-parameter OCR model โ runs on CPU, 15ร faster than Tesseract, with accuracy close to that of models with 1B+ parameters
Search inside documents, code, and even screenshots โ instantly and locally. A free, open-source file launcher with OCR, semantic search, and MCP agent access.
A lightweight OCR system based on PaddleOCR, decoupled from the PaddlePaddle deep learning training framework, with ultra-fast inference speed.
A collection of original, innovative ideas and algorithms towards Advanced Literate Machinery. This project is maintained by the OCR Team in the Language Technology Lab, Tongyi Lab, Alibaba Group.
High-performance, privacy-first on-device AI inference library for React Native, powered by PyTorch's ExecuTorch runtime
YomiToku is a Python package that provides an AI-powered Japanese document analysis engine. Yomitoku is an AI-powered document image analysis package designed specifically for the Japanese language.
Fast and efficient unstructured data extraction. Written in Rust with bindings for many languages.
MixTeX multimodal LaTeX, ZhEn, and, Table OCR. It performs efficient CPU-based inference in a local offline on Windows.
ExtractThinker is a Document Intelligence library for LLMs, offering ORM-style interaction for flexible and powerful document workflows.
Collection of open-source libraries and tools for Robotic Process Automation (RPA), designed to be used with both Robot Framework and Python
Extract and convert data from any document, images, pdfs, word doc, ppt or URL into multiple formats (Markdown, JSON, CSV, HTML) with intelligent structured data extraction and advanced OCR.
Open-source screenshot and screen recording for macOS. The free, native alternative to CleanShot X. Built with Swift 6.0 and SwiftUI.
OpenOCR: An Open-Source Toolkit for General-OCR Research and Applications, integrates a unified training and evaluation benchmark, commercial-grade OCR and Document Parsing systems, and faithful reproductions of the core implementations from a wide range of academic papers.
OCR offline image text recognition command-line program for Windows, outputting results in JSON string format for easy invocation by other programs. Provides APIs in various languages. Compiled from PaddleOCR C++.
Open-source platform for extracting structured data from documents using AI.
A packaged and flexible version of the CRAFT text detector and Keras CRNN recognition model.
A group of notebooks and other files which can help you learn AI from scratch.
A self-hosted, resource-aware file conversion server supporting 530 formats in 26 languages.
Mouseover Translate Any Language At Once - Chrome Extension: PDF Translator, EBOOK, EPUB, OCR, TTS, NETFLIX, YOUTUBE DUAL SUBTITLES, GOOGLE DOCS, AI, VIEWER, GMAIL, WRITING, IMAGE, DUALSUBS, MANGA, HOVER, DICTIONARY, WEBTOON, EDGE, JAPANESE, ENGLISH
How to Copy Text from Images ? Answer is TextSnatcher !. Perform OCR operations in seconds on Linux Desktop.
Open-source no-root Android real-time screen translator for games, visual novels, and manga. Supports on-device and cloud OCR, offline LLMs, multiple translation services, on-screen translations, and text-to-speech (TTS).
Computer use for about $0.0002 a step: OCR the screen, classify the next action with TypeSafe, click. macOS.
:art: Math Formula OCR Pro: Enhanced Version for Recognizing Handwritten and Printed Formulas in Chinese and English, Supports Basic Symbol Reasoning (Data Structure Based on LaTeX Abstract Syntax Tree). Supports handwrite, Chinese-mixed formulas and simple symbol reasoning (based on LaTeX AST).