Skip to content
Is there an AI for this?

Alternatives

Self-hosted alternatives to Amazon Textract

Projects in the registry that can run on your own hardware and serve at least one of the same use cases as Amazon Textract.

Source
Registry relations over fetched repository records — the evidence sits on each repository page
Verified
Evidence not verified
Confidence
High

01How this list was built

Compared against
Amazon Textract
Delivery
SaaS products
Shared use cases
OCR, Invoice extraction, Data extraction
Selection rule
open source, or self-hostable, and shares a use case
Candidates found
12

02Alternatives

12

  • Docling

    Libraries

    Document conversion toolkit that parses PDF, Office and image files into structured Markdown or JSON, preserving reading order, tables and figures for downstream retrieval.

    Repository
    docling-project/docling
    Stars
    65,519
    Licence
    MIT
    In stacks
    5

    Shares: Ocr · Data extraction

  • LlamaIndex

    Frameworks

    Data framework for retrieval applications: loaders for many document types, indexing and query pipelines, and evaluation helpers for retrieval quality.

    Repository
    run-llama/llama_index
    Stars
    52,226
    Licence
    MIT
    In stacks
    0

    Shares: Data extraction

  • LocalAI

    Model servers

    Drop-in OpenAI-compatible API server that runs text, embedding, image and audio models locally across several back ends, including CPU-only deployments.

    Repository
    mudler/LocalAI
    Stars
    49,166
    Licence
    MIT
    In stacks
    0

    Shares: Ocr

  • Marker

    Libraries

    PDF-to-Markdown converter aimed at long documents, with optional model-assisted correction. Published under a licence with a revenue condition — read it before commercial use.

    Repository
    datalab-to/marker
    Stars
    39,841
    Licence
    Apache-2.0
    In stacks
    0

    Shares: Ocr

  • Milvus

    Hybrid — hosted or self-hosted

    Distributed vector database designed for large collections, with several index types, GPU indexing options and a separated storage and compute architecture.

    Repository
    milvus-io/milvus
    Stars
    46,159
    Licence
    Apache-2.0
    In stacks
    0

    Shares: Data extraction

  • MinerU

    Libraries

    Converts PDFs to structured Markdown or JSON, keeping reading order, tables and formulae. Handles Chinese layouts, which most Western-trained parsers do poorly.

    Repository
    opendatalab/MinerU
    Stars
    80,242
    Licence
    Other
    In stacks
    0

    Shares: Ocr · Data extraction

  • olmOCR

    Libraries

    Vision-language OCR pipeline from AI2 for turning page images into linearised text at scale, with the model weights published alongside the toolkit.

    Repository
    allenai/olmocr
    Stars
    19,631
    Licence
    Apache-2.0
    In stacks
    0

    Shares: Ocr · Data extraction

  • PaddleOCR

    Libraries

    OCR toolkit with detection, recognition and layout models, including Chinese and other East Asian scripts, plus table and formula recognition. Runs offline on CPU or GPU.

    Repository
    PaddlePaddle/PaddleOCR
    Stars
    88,941
    Licence
    Apache-2.0
    In stacks
    0

    Shares: Ocr · Data extraction

  • paperless-ngx

    Self-hosted projects

    Self-hosted document management system that OCRs incoming scans and email, applies tags and correspondents through trainable rules, and keeps a searchable archive.

    Repository
    paperless-ngx/paperless-ngx
    Stars
    44,585
    Licence
    GPL-3.0
    In stacks
    2

    Shares: Ocr · Invoice extraction

  • RAGFlow

    Self-hosted projects

    Retrieval engine built around deep document parsing: layout-aware chunking of PDFs, tables and scans, citation-backed answers, and a visual pipeline for building knowledge bases.

    Repository
    infiniflow/ragflow
    Stars
    90,113
    Licence
    Apache-2.0
    In stacks
    1

    Shares: Data extraction

  • Tesseract OCR

    Libraries

    Long-established open-source OCR engine with trained data for many languages and scripts, usable offline and embedded in most self-hosted document pipelines.

    Repository
    tesseract-ocr/tesseract
    Stars
    76,569
    Licence
    Apache-2.0
    In stacks
    0

    Shares: Ocr · Data extraction

  • Unstructured

    Hybrid — hosted or self-hosted

    Library and hosted API that partition documents of many formats into typed elements for indexing, with connectors to common storage systems and vector databases.

    Repository
    Unstructured-IO/unstructured
    Stars
    15,454
    Licence
    Apache-2.0
    In stacks
    1

    Shares: Data extraction · Ocr

03Repository facts

RepositoryStarsHealth
docling-project/doclingGet your documents ready for gen AI66kMaintenance 60%, Releases 60%, Contributors 50%, Issues 85%, Community 96%70
run-llama/llama_indexLlamaIndex is the document processing platform for AI52kMaintenance 80%, Releases 60%, Contributors 50%, Issues 85%, Community 94%76
mudler/LocalAILocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.49kMaintenance 80%, Releases 80%, Contributors 50%, Issues 97%, Community 94%81
datalab-to/markerConvert PDF to markdown + JSON quickly with high accuracy40kMaintenance 60%, Releases 60%, Contributors 50%, Issues 88%, Community 92%69
milvus-io/milvusMilvus is a high-performance, cloud-native vector database built for scalable vector ANN search46kMaintenance 80%, Releases 60%, Contributors 50%, Issues 69%, Community 93%74
opendatalab/MinerUTransforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.80kMaintenance 80%, Releases 80%, Contributors 50%, Issues 99%, Community 98%82
allenai/olmocrToolkit for linearizing PDFs for LLM datasets/training20kMaintenance 20%, Releases 20%, Contributors 50%, Issues 95%, Community 86%49
PaddlePaddle/PaddleOCRTurn 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.89kMaintenance 60%, Releases 40%, Contributors 50%, Issues 97%, Community 99%68
paperless-ngx/paperless-ngxA community-supported supercharged document management system: scan, index and archive all your documents45kMaintenance 60%, Releases 60%, Contributors 50%, Issues 100%, Community 93%71
infiniflow/ragflowRAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs90kMaintenance 60%, Releases 60%, Contributors 50%, Issues 82%, Community 99%71
tesseract-ocr/tesseractTesseract Open Source OCR Engine (main repository)77kMaintenance 60%, Releases 60%, Contributors 50%, Issues 94%, Community 98%71
Unstructured-IO/unstructuredConvert 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.15kMaintenance 60%, Releases 60%, Contributors 50%, Issues 80%, Community 84%66

04Ask about your own case

Which alternative is right depends on how many people will use it, what the data is and what you can operate. Ask and the answer is researched for your organisation.

  1. 01What is a self-hosted alternative to Amazon Textract that we can run ourselves?