Alternatives to Box in 2026

PaddleOCR PaddlePaddle

Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

Building block Production-ready You need strong OCR, especially for Chinese and Asian scripts, in a document pipeline.

★ 92k Apache-2.0 Python Active, pushed 2 months ago

Tesseract tesseract-ocr

Tesseract Open Source OCR Engine (main repository)

Building block Production-ready You need free, offline OCR for reasonably clean printed text.

★ 77k Apache-2.0 C++ Active, pushed 5 days ago

Docling docling-project

Get your documents ready for gen AI

Building block Production-ready You feed business documents into RAG or LLM workflows and need reliable local parsing.

★ 70k MIT Python Active, pushed yesterday

Paperless-ngx paperless-ngx

A community-supported supercharged document management system: scan, index and archive all your documents

Complete system Production-ready A household or small office wants to go paperless and can run Docker.

★ 47k GPL-3.0 Python Active, pushed 4 days ago

OCRmyPDF ocrmypdf

OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched

Developer tool Production-ready You have scanned PDFs that need to become searchable, in batch or a pipeline.

★ 35k MPL-2.0 Python Active, pushed 9 days ago

OpenDataLoader PDF opendataloader-project

PDF Parser for AI-ready data. Automate PDF accessibility. Open-source.

Building block Usable You need fast, deterministic PDF extraction locally, with an optional AI mode for hard pages.

★ 30k Apache-2.0 Java Active, pushed 4 days ago

Pdf-inspector firecrawl

Fast Rust library for PDF inspection, classification, and text extraction. Intelligently detects scanned vs text-based PDFs to enable smart routing decisions.

Building block Usable Your pipeline processes many PDFs and you want to skip OCR where text is already present.

★ 20k MIT Rust Active, pushed 11 days ago

Unstructured Unstructured-IO

Convert documents to structured data effortlessly. Unstructured is open-source ETL solution for transforming complex documents into clean, structured formats for language models. Visit our website to learn more about our enterprise grade Platform product for production grade workflows, partitioning, enrichments, chunking and embedding.

Building block Production-ready You are building document ingestion for an LLM app and need many file types handled.

★ 16k Apache-2.0 HTML Active, pushed 4 days ago

Skill_Seekers yusufkaraaslan

Convert documentation websites, GitHub repositories, and PDFs into Claude AI skills with automatic conflict detection

Developer tool Usable You want Claude to work from a library's docs without hand-writing a skill.

★ 15k MIT Python Active, pushed 33 days ago

Easydict tisfeng

一个简洁优雅的词典翻译 macOS App。开箱即用，支持离线 OCR 识别，支持有道词典，🍎 苹果系统词典，🍎 苹果系统翻译，OpenAI，Gemini，DeepL，Google，Bing，腾讯，百度，阿里，小牛，彩云和火山翻译。A concise and elegant Dictionary and Translator macOS App for looking up words and translating text.

Complete system Production-ready You read or write in several languages on a Mac and want quick lookups.

★ 15k GPL-3.0 Swift Active, pushed 7 days ago

LunaTranslator HIllya51

视觉小说翻译器 / Visual Novel Translator

Complete system Production-ready You play Japanese visual novels and want live translation.

★ 14k GPL-3.0 C++ Active, pushed 15 days ago

LiteParse run-llama

A fast, helpful, and open-source document parser

Building block Usable You want a fast local parser before sending documents into an LLM pipeline, perhaps alongside LlamaIndex.

★ 13k Apache-2.0 Rust Active, pushed 7 days ago

Chandra datalab-to

OCR model that handles complex tables, forms, handwriting with full layout.

Building block Usable You need high-accuracy OCR on difficult documents and have a GPU or are fine with Datalab's API.

★ 13k Apache-2.0 Python Active, pushed 11 days ago

BISHENG dataelement

BISHENG is an open LLM devops platform for next generation Enterprise AI applications. Powerful and comprehensive features include: GenAI workflow, RAG, Agent, Unified model management, Evaluation, SFT, Dataset Management, Enterprise-level System Management, Observability and more.

Framework or platform Usable A large organisation, particularly in China, wants a self-hosted platform for building internal AI apps.

★ 12k Apache-2.0 Python Active, pushed 2 days ago

PyMuPDF pymupdf

PyMuPDF is a high performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.

Building block Production-ready You process PDFs in Python and need speed and breadth.

★ 11k AGPL-3.0 Python Active, pushed 4 days ago

X-AnyLabeling CVHub520

X-AnyLabeling: A lightweight, efficient, and unified cross-platform desktop application for annotating text, image, video, point cloud and multimodal data, combining versatile built-in tools with state-of-the-art AI models and flexible multi-format export.

Developer tool Production-ready You build computer-vision datasets and want AI-assisted labelling on your own machine.

★ 11k GPL-3.0 Python Active, pushed 2 days ago

Manga Image Translator zyddnys

Translate manga/image 一键翻译各类图片内文字 https://cotrans.touhou.ai/ (no longer working)

Complete system Usable You want machine-translated manga pages and can run a GPU model locally.

★ 11k GPL-3.0 Python Active, pushed 22 days ago

Xberg xberg-io

Polyglot document intelligence with a Rust core: extract text, metadata, images, tables, and structured data from 106 formats across 140 file extensions, plus code intelligence for 371 languages. Fifteen bindings, with CLI, REST API, and MCP server.

Building block Usable You need one extraction library across many file types and languages.

★ 9.5k MIT Rust Active, pushed 6 days ago

STranslate STranslate

A ready-to-go translation ocr tool developed with WPF/WPF 开发的一款即用即走的翻译、OCR工具

Complete system Production-ready You work on Windows and often need to translate snippets or text in images.

★ 8.5k MIT C# Active, pushed 40 days ago

Jev-chat-jarvis jev-chat

The chat decision assistant: before you reply, Jev reads the chat, judges intent and risk, and drafts replies you fill in with one tap. You press send. Android · Windows · macOS · iOS | 聊天辅助决策工具：先看懂对方再回复，发不发由你。

★ 8.2k MIT Kotlin Active, pushed yesterday

Tesseract.js naptha

Pure Javascript OCR for more than 100 Languages 📖🎉🖥

Building block Production-ready You want OCR client-side in a web app without a server.

★ 39k Apache-2.0 JavaScript Slowing, pushed 6 months ago

GLM-OCR zai-org

GLM-OCR: Accurate × Fast × Comprehensive

Building block Experimental You want a recent open OCR model for difficult documents and can host it on a GPU.

★ 7.5k Apache-2.0 Python Active, pushed 20 days ago

eSearch xushengfeng

截屏 离线OCR 搜索翻译 以图搜图 贴图 录屏 万向滚动截屏 屏幕翻译 Screenshot Offline OCR Search Translate Search for picture Paste the picture on the screen Screen recorder Omnidirectional scrolling screenshot Screen translator 支持Windows Linux macOS

Complete system Production-ready You want one free tool for screenshots plus OCR and translation, especially on Linux.

★ 7.4k GPL-3.0 TypeScript Active, pushed today

Unstract Zipstack

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

Complete system Usable A team processes invoices, forms or contracts at volume and wants LLM extraction it can host.

★ 7.3k AGPL-3.0 Python Active, pushed 6 days ago

PDF Craft oomol-lab

PDF craft can convert PDF files into various other formats. This project will focus on processing PDF files of scanned books.

Building block Usable You need to digitise scanned books into clean ebooks and have a GPU.

★ 6.5k MIT Python Active, pushed yesterday

EasyOCR JaidedAI

Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.

Building block Usable You need quick multilingual OCR in Python, especially for photos and scene text.

★ 30k Apache-2.0 Python Slowing, pushed 11 months ago

docTR mindee

docTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning. Ongoing development and maintenance by t2k.

Building block Production-ready You want trainable deep-learning OCR in Python that you can fine-tune on your own documents.

★ 6.4k Apache-2.0 Python Active, pushed 2 days ago

PaddleX PaddlePaddle

All-in-One Development Tool based on PaddlePaddle

Framework or platform Production-ready You want ready model pipelines and already use or accept the PaddlePaddle ecosystem.

★ 6.3k Apache-2.0 Python Active, pushed 13 days ago

Paperless-AI clusterzx

An automated document analyzer for Paperless-ngx using OpenAI API, Ollama, Deepseek-r1, Azure and all OpenAI API compatible Services to automatically analyze and tag your documents.

Integration Usable Only if you already run it; check forks or paperless-gpt for new setups.

★ 6k MIT JavaScript Active, pushed 18 days ago

Translumo ramjke

Advanced real-time screen translator for games, hardcoded subtitles in videos, static text and etc.

Complete system Usable You play games or watch videos in a language you do not read and use Windows.

★ 5.9k Apache-2.0 C# Active, pushed 42 days ago

BallonsTranslator dmMaze

深度学习辅助漫画翻译工具, 支持一键机翻和简单的图像/文本编辑 | Yet another computer-aided comic/manga translation tool powered by deeplearning

Complete system Usable A fan translator wants a machine-assisted workflow they can correct by hand.

★ 5.2k GPL-3.0 Python Active, pushed 10 days ago

Text Grab TheJoeFin

Use OCR in Windows quickly and easily with Text Grab. With optional background process and notifications.

Complete system Production-ready You often need to copy text out of images, videos or locked apps on Windows.

★ 5.1k MIT C# Active, pushed 7 days ago

Paperless-gpt icereed

Use LLMs and LLM Vision (OCR) to handle paperless-ngx - Document Digitalization powered by AI

Integration Usable You run Paperless-ngx and want better OCR and metadata through a local or cloud model.

★ 2.8k MIT Go Active, pushed 13 days ago

Docs sismics

Lightweight document management system packed with all the features you can expect from big expensive solutions

Complete system Usable A small business or individual wants a simple DMS that runs in one Docker container.

★ 2.6k GPL-2.0 JavaScript Active, pushed 16 days ago

Docspell eikek

Assist in organizing your piles of documents, resulting from scanners, e-mails and other sources with miminal effort.

Complete system Usable You want a paperless archive with stronger automatic metadata suggestions and can run a JVM service.

★ 2.3k AGPL-3.0 Elm Active, pushed 7 days ago

Readur readur

Quick, painless, intuitive OCR platform written in Rust and TypeScript. Modern UI with modern API, with an emphasis on intuitive user experience.

Complete system Usable You want a Paperless-style archive with a modern API and a fast Rust backend.

★ 808 MIT Rust Active, pushed 8 days ago

Nuxeo nuxeo

Content management platform to build modern business applications

Framework or platform Production-ready You are building a large document or asset management application on a Java stack.

★ 709 Apache-2.0 Java Active, pushed today

Papermerge-core papermerge

Papermerge OSS

Complete system Usable You want a folder-based archive for scanned paperwork with page-level editing.

★ 550 Apache-2.0 Python Active, pushed 2 days ago

Docfd darrenldl

TUI multiline fuzzy document finder

Developer tool Usable You search your own documents from the terminal and grep is too literal.

★ 292 MIT OCaml Active, pushed 14 days ago

OpenDocMan opendocman

OpenDocMan - Free PHP Document Management System DMS

Complete system Usable A small lab needs basic controlled-document management on PHP hosting.

★ 283 GPL-2.0 PHP Active, pushed 2 months ago

Stapler gingerbeardman

My take on the classic Macintosh app Stapler (with a little bit of LaunchList)

Complete system Usable You often open the same set of files and apps together on a Mac.

★ 281 MIT Swift Active, pushed 2 months ago

Zettelrobbe admonstrator

Next-generation fork of Paperless-AI for Paperless-ngx: reliable AI tagging plus an OCR rescue queue (Mistral or local vision models, multi-page PDFs), failed/ignored document queues, one-click rescan history, MFA, guided setup, and richer custom fields.

Integration Experimental You run Paperless-ngx and want AI tagging from a more actively maintained Paperless-AI fork.

★ 268 MIT JavaScript Active, pushed 4 days ago

Alfresco-community-repo Alfresco

Community Content Service Repository

Building block Production-ready You build or maintain an Alfresco Community installation and need the repository source.

★ 240 LGPL-3.0 Java Active, pushed 6 days ago

WP Document Revisions wp-document-revisions

Document management and version control for WordPress. Collaborate on files, track every revision, and auto-generate change summaries with AI.

Integration Production-ready Your team already lives in WordPress and needs simple version-controlled documents there.

★ 178 GPL-3.0 PHP Active, pushed 13 days ago

EveryDocs Core jonashellmann

A simple Document Management System for private use with basic functionality to organize your documents digitally

Complete system Usable You want a very basic personal document store and prefer Rails.

★ 421 GPL-3.0 Ruby Slowing, pushed 3 months ago

SimpleDMS simpledms

Document management for small businesses.

Complete system Usable A small business wants a simple self-hosted DMS without running a database server.

★ 170 AGPL-3.0 Go Active, pushed 13 days ago

AI-WorkDeck AI-WorkDeck

Open-source AI workspace shaped by everyday legal practice and colleagues’ feedback, developed with team support. Documents, reviewable AI edits, linked sources, and project history.

Complete system Experimental A small law firm or legal team wants to try AI-assisted drafting on its own machines with reviewable changes.

★ 169 AGPL-3.0 JavaScript Active, pushed 3 days ago

Document-chat-system watat83

Open-source document chat platform with semantic search, RAG (Retrieval Augmented Generation), and multi-provider AI support (OpenRouter, OpenAI, ImageRouter).

Template or starter Experimental You want a starting codebase for a chat-with-your-documents product.

★ 148 MIT TypeScript Active, pushed 27 days ago

I-librarian-free mkucej

I, Librarian - open-source version of a PDF managing SaaS.

Complete system Usable A researcher or lab wants a self-hosted reference and PDF library.

★ 353 GPL-3.0 PHP Slowing, pushed 11 months ago

Community logicaldoc

LogicalDOC Community open source document management system https://www.logicaldoc.com

Complete system Production-ready An office wants a conventional DMS with a commercial upgrade path.

★ 146 LGPL-3.0 Java Active, pushed 9 days ago

Zena Zena-Linux

Zena is a bootc-based, immutable Linux desktop focused on performance and modern Wayland workflows. It ships with the Cachy kernel, Niri, MangoWC, and Dank Material Shell.

Complete system Experimental A Linux enthusiast wants an opinionated, reproducible tiling Wayland desktop.

★ 143 Apache-2.0 Shell Active, pushed 3 months ago

Blueking-dbm TencentBlueKing

DBM，数据库管理，集成了MySQL、Redis、ES、Kafka、HDFS、InfluxDB、Pulsar等多种数据库组件的全生命周期管理，提供了海量集群的批量管理能力，以及相应DB组件的集群管理工具箱，并配套DB个性化配置、高可用切换、域名管理等DB个性化服务，同时全方位的监控告警可观测能力，让数据库管理员、运维、开发等用户可以轻松完成数据库管理工作，更高效、更安全、更全面的管理数据库。 The database management platform integrates a variety of database components such as MySQL...

Complete system Usable A large operations team already on Tencent BlueKing needs to manage many database clusters.

★ 124 MIT Python Active, pushed 3 days ago

DocsMint HiAi-gg

Open-source knowledge base for people and AI agents. Rich-text editing, hybrid search, GraphRAG, and MCP. Self-host with Docker or use DocsMint Cloud.

Complete system Experimental A team wants its documentation searchable by both people and AI agents on its own server.

★ 109 Apache-2.0 TypeScript Active, pushed 7 days ago

Ackify kOlapsis

🔏 Proof of Read. Compliance made simple.

Complete system Usable A company must show auditors that staff acknowledged policies, and wants a small self-hosted tool.

★ 209 AGPL-3.0 Go Slowing, pushed 3 months ago

Fadocx anonfaded

All-in-one offline document viewer for Android with OCR and desktop-class rendering — private, open-source, zero tracking

Complete system Usable You want to open documents on Android without cloud services or tracking.

★ 39 GPL-3.0 Dart Slowing, pushed 6 months ago

Dms gavin1995

基于Json Schema的动态Json数据配置平台

Building block Experimental Rarely; the author announced a rewrite in 2021 that never shipped.

★ 164 MIT JavaScript Quiet, pushed 17 months ago

DigiDocu harish81

Open Source Documents Management System Built with Laravel 10

Complete system Experimental Only as a base for your own Laravel document app.

★ 142 GPL-3.0 PHP Quiet, pushed 3 years ago

Templated-docs alexmorozov

Generate PDF, MS Word and Excel documents from templates in Django

Building block Experimental Rarely; it has been idle since 2022.

★ 115 MIT Python Quiet, pushed 4 years ago

Trina AX trina-app

Self-hosted team AI workspace for company files, with per-person folder permissions. Claude Code, Codex CLI, skills, MCP and schedules.

Complete system Experimental A company wants non-developers to use coding agents on shared files without each installing them.

★ 3 AGPL-3.0 TypeScript Active, pushed 3 days ago

Microsoft SharePoint Microsoft

Web platform part of Microsoft 365

Complete system Production-ready An organisation on Microsoft 365 wants document storage, intranet and records management with no extra licence.

2.7k readers a month Commercial

Azure AI Document Intelligence Microsoft

Explore Azure Document Intelligence (as part of Azure Content Understanding in Foundry Tools). Extract document text, structure, and fields with AI models.

Building block Production-ready A team on Azure needs to extract structured data from invoices, forms or contracts.

Commercial

ABBYY FineReader ABBYY

ABBYY's latest AI-based OCR technology powers this PDF editor software. Use tool to convert files (PDF to Excel, PDF to Word, etc.), edit, share, collaborate & more!

Complete system Production-ready You regularly need accurate OCR of scanned documents into editable formats on your own computer.

143 readers a month Since 1993 Commercial

Amazon Textract Amazon Web Services

Amazon Textract is a machine learning (ML) service that uses optical character recognition (OCR) to automatically extract text, handwriting, and data from scanned PDF documents, forms, and tables.

Building block Production-ready You build document pipelines on AWS and need OCR plus table and form extraction at scale.

Commercial

Google Document AI Google

The Document AI solutions suite includes pretrained models for document processing, Workbench for custom models, and Warehouse to search and store.

Building block Production-ready Your team runs on Google Cloud and needs document extraction with custom processors.

Commercial

DocuWare DocuWare

DocuWare is a leading provider of document management software & solutions. Improve your document processing today with workflow automation software.

Complete system Production-ready A midsize company wants to digitise paper-heavy processes like accounts payable or HR records, usually through a local reseller.

96 readers a month Since 1988 Commercial

Hyland OnBase Hyland Software

Discover OnBase, a leading content management product to efficiently manage information and streamline business processes for optimal performance.

Complete system Production-ready A hospital, insurer or public agency needs document-centric workflows tied to core line-of-business systems.

Commercial

M-Files M-Files

M-Files helps you organize documents in context, automate workflows, and reduce risk with secure, AI-powered document management system software.

Complete system Production-ready An engineering, professional services or regulated firm wants controlled documents and approval workflows without migrating every file store.

Commercial

OpenText Documentum OpenText

OpenText Documentum Content Management is highly secure, compliant, cloud-ready document management software that scales to meet complex, high-volume needs

Complete system Production-ready A large regulated enterprise needs validated, auditable document control at scale and already has Documentum expertise.

Commercial

Laserfiche Laserfiche

Get work done faster with Laserfiche, the leading provider of AI-powered document management and process automation. Through powerful workflows, electronic forms, document management and analytics, Laserfiche accelerates processes enterprise-wide.

Complete system Production-ready A government body, school or midsize organisation wants records management plus forms-driven workflows.

Commercial

NetDocuments NetDocuments

Save time, money, and frustration! Automate your document and email management with NetDocuments' secure, compliant and "anywhere accessible" platform.

Complete system Production-ready A law firm wants matter-centric document management in the cloud rather than an on-premise DMS.

Commercial

Rossum Rossum

Automate complex transactional workflows with Rossum’s AI document processing solution. Reduce manual tasks, increase accuracy, drive efficiency.

Complete system Production-ready An AP or logistics team processes large volumes of varied supplier documents and wants extraction with human review.

Commercial