Data, search & knowledge

Document processing & OCR

1,074 agents · most starred first

Document processing & OCR, page 10 of 11

swarmauri_ocr_pytesseract

Swarmauri Tesseract Image to Text Model

swarmauri_parser_asn1

Grammar-driven ASN.1 (X.680/X.690 DER subset) parser plugin for swarmauri-sdk using Lark Earley.

swarmauri_parser_beautifulsoupelement

BeautifulSoup Element Parser for Swarmauri.

swarmauri_parser_entityrecognition

Entity Recognition Parser for Swarmauri.

swarmauri_parser_fitzpdf

Fitz PDF Parser for Swarmauri.

swarmauri_parser_keywordextractor

Keyword Extractor Parser for Swarmauri.

swarmauri_parser_pypdf2

PyPDF2 Parser for Swarmauri.

swarmauri_parser_pypdftk

A parser for extracting text from PDFs using PyPDFTK.

swarmauri_parser_slate

A parser for extracting text from PDFs using Slate.

swarmauri_parser_textblob

TextBlob Parser for Swarmauri.

swarmauri_tool_downloadpdf

Swarmauri Community Download PDF Tool

swarmauri_tool_entityrecognition

Swarmauri Community Entity Recognition Tool

swarmauri_tool_jupyterclearoutput

A tool designed to clear all outputs from a Jupyter Notebook using nbconvert’s ClearOutputPreprocessor, preparing the notebook for sharing or version control.

swarmauri_tool_jupyterdisplay

A tool designed to display rich media and object representations in a Jupyter Notebook using IPython's display functionality.

swarmauri_tool_jupyterdisplayhtml

A tool designed to render HTML content within a Jupyter Notebook using IPython's HTML display method.

swarmauri_tool_jupyterexecuteandconvert

A tool that programmatically executes and converts a Jupyter Notebook using nbconvert's CLI functionality, enabling automated notebook execution and format conversion.

swarmauri_tool_jupyterexecutecell

A tool designed to execute a single code cell in a running Jupyter kernel using jupyter_client, capturing its output and errors.

swarmauri_tool_jupyterexecutenotebook

A tool designed to execute all cells in a Jupyter Notebook using nbconvert’s ExecutePreprocessor, capturing outputs for testing and reporting.

swarmauri_tool_jupyterexecutenotebookwithparameters

A tool designed to execute parameterized notebooks using papermill, allowing dynamic input and output capture for automated workflows.

swarmauri_tool_jupyterexporthtml

A tool that exports a Jupyter Notebook to HTML format using nbconvert’s HTMLExporter, enabling web-based presentation of notebooks.

swarmauri_tool_jupyterexportlatex

A tool that exports a Jupyter Notebook to LaTeX format using nbconvert’s LatexExporter, enabling further conversion to PDF.

swarmauri_tool_jupyterexportmarkdown

A Swarmauri tool designed to export Jupyter Notebooks to Markdown.

swarmauri_tool_jupyterexportpython

A tool that exports a Jupyter Notebook to a Python script using nbconvert’s PythonExporter, facilitating code extraction.

swarmauri_tool_jupyterfromdict

A tool that converts a plain dictionary into a NotebookNode object using nbformat, facilitating programmatic notebook creation.

swarmauri_tool_jupytergetiopubmessage

A tool designed to retrieve messages from the IOPub channel of a Jupyter kernel using jupyter_client, capturing cell outputs and logs.

swarmauri_tool_searchword

A tool for searching a specific word or phrase in a file.

swarmauri_xmp_gif

GIF handler for embedding and extracting XMP packets in Swarmauri runtimes.

swarmauri_xmp_jpeg

JPEG handler for embedding and extracting XMP packets in Swarmauri runtimes.

swarmauri_xmp_mp4

ISO-BMFF handler scaffold for embedding and extracting XMP packets in Swarmauri runtimes.

swarmauri_xmp_pdf

PDF handler scaffold for embedding and extracting XMP packets in Swarmauri runtimes.

swarmauri_xmp_png

PNG handler for embedding and extracting XMP packets in Swarmauri runtimes.

swarmauri_xmp_svg

SVG handler for embedding and extracting XMP packets in Swarmauri runtimes.

swarmauri_xmp_tiff

TIFF/DNG handler scaffold for embedding and extracting XMP packets in Swarmauri runtimes.

swarmauri_xmp_webp

WebP handler scaffold for embedding and extracting XMP packets in Swarmauri runtimes.

table2llm

Parse complex tables from CSV, XLSX, and DOCX into JSON/Markdown/HTML)

textify4llm

Converts any file format into plaintext/JSON, enabling multimodality for any LLM

to-paragraphs
transformgpt

A library for transforming unstructured text into structured data without context/mappings using ChatGPT.

txtstorage

silly silly sily suilly isilly silly

types-boto3-bedrock-data-automation

Type annotations for boto3 DataAutomationforBedrock 1.44.0 service generated with mypy-boto3-builder 8.12.0

types-boto3-bedrock-data-automation-runtime

Type annotations for boto3 RuntimeforBedrockDataAutomation 1.44.0 service generated with mypy-boto3-builder 8.12.0

unicms-unical-storage-handler

uniCMS handler to display data from storage.unical.it APIs

unidoc-agent

Universal Document Agent for extracting and analyzing various documents with Ollama support.

unstructured-fileconverter-haystack

Haystack 2.x component to convert files into Documents using the Unstructured API

vllmocr

OCR using LLMs

wizit-open-rag

AI-powered document transcription and semantic chunking for RAG pipelines

zendatastorage

A Python package for processing data from .zenf files.

intelliparse

IntelliParse review: compare features, pricing, use cases, access model, and alternatives for this AI Docs Agents agent in 2026. Multimodal Document Ingestor Agent AI-infused automation requires more than a roster of agents

LlamaCloud

LlamaCloud helps AI process complex documents for smart search.

llm-json-extract

Extract & validate JSON from messy LLM output. Designed for Claude / Codex CLI workflows where tool-use is unavailable. XML-tag aware, with multi-stage fallbacks and jsonrepair.

markitdown-mcp-npx

NPX wrapper for Microsoft's MarkItDown MCP server - run without Docker. Provides the same file conversion capabilities (PDF, Word, Excel, images, etc.) as the original Docker version but with easier setup and direct file system access.

office2sdp

This is a tool for converting the output yaml from officeDev api-documenter tool to new content structure.

Hebbia AI

AI for serious work: analyze complex documents and data fast.

@agentic-db/documents-loader

Load, import, and export markdown/text files into the agentic-db documents table

@pappacena/n8n-nodes-agentic-doc

n8n node for LandingAI agentic document parsing

@virstack/doc-ingest

A high-performance, parallelized document ingestion and vectorization pipeline.

@superdoc-dev/ai

AI integration package for SuperDoc

pixelrag-render

Document to image tiles. Renders web pages, PDFs, and local files as tiled screenshots.

wondershare-recoverit

Wondershare Recoverit review: compare features, pricing, use cases, access model, and alternatives for this Other agent in 2026. ai data recovery, recoverit ai recovery, ai video recovery, ai image recovery

vid2llm

Turn any video into LLM-ready frames. Smart sampling, scene detection, OCR, and SDK-ready output for modern multimodal language models.

@json-render/yaml

YAML wire format for @json-render/core. Progressive rendering and surgical edits via streaming YAML.

pymupdf4llm-tsr

PyMuPDF Utilities for LLM/RAG with Visual Analyzer

heicpdfto

HEICPDF.TO review: compare features, pricing, use cases, access model, and alternatives for this Other agent in 2026. Convert Apple HEIC photos to PDF documents online

azure-di-financial-haystack

Haystack components for structured KV extraction from financial PDFs via Azure Document Intelligence

llama-index-readers-azure-tax-forms

LlamaIndex reader for IRS tax form extraction via Azure Document Intelligence — supports Form 1040, W-2, Schedule C/E/K-1, 1065, 1120, 1120-S

mllm-annotator

Resumable multimodal-LLM annotator and embedder for folders of audio or image files.

event-extraction-agent

Python library for extracting structured event data from text posts with LLM agents.

pepsico-document-agents

Agent-based extraction framework for transforming parsed documents into structured planogram data

tika-haystack

Haystack integration for Apache Tika document conversion

agent-markitdown

Safe local document-to-markdown preprocessing for OpenClaw, Claude Code, Codex, Hermes, and other agents.

akshu-finagent

Financial statement PDF extraction agent

pyjsonfrag

Combined tree/event based JSON parser

agent-markdown-pdf

Agent-friendly Markdown-to-PDF CLI with HTML preview and JSON diagnostics

azure-form-recognizer-haystack

Haystack integration for Azure Document Intelligence using the Form Recognizer SDK

runic-rag-docling

Optional Docling adapters implementing the runic.rag DocumentParser/DocumentChunker ports.

asyagent

An HTTP service that compiles Asymptote (*.asy) sources into rendered output (PDF, SVG, EPS, PNG, JPG).

@lightfeed/extractor

Use LLMs to robustly extract and enrich structured data from HTML and markdown

agentcontext-core

Document parsing that never loses provenance: every block of output knows its source page, section, and location.

docling-ocr-mistral

Mistral OCR plugin for Docling

langchain-pdfmuse

LangChain document loader for pdfmuse — deterministic PDF/DOCX parsing for RAG.

llama-index-readers-pdfmuse

LlamaIndex reader for pdfmuse — deterministic PDF/DOCX parsing for RAG.

pdfmuse-haystack

Haystack converter for pdfmuse — deterministic PDF/DOCX parsing for RAG.

semos-agentura-document

Document digestion (OCR to Markdown) and composition (Markdown to documents) agent

marker-pdf-agent

Document conversion agent that watches folders, converts files with marker-pdf, and routes Markdown outputs.

@sinoia/hubdoc-tools

Professional command-line tool for HubDoc document management and bulk import/export

@xberg-io/langchain-xberg

LangChain.js document loader for Xberg — extract text, tables, and metadata from 107 document formats with optional OCR.

docimprint

Official TypeScript SDK for the DocImprint document intelligence API

agent-folder-workspace

Offline, lazy, agent-oriented exploration of heterogeneous folders

agent-pdf-workspace

Offline, agent-oriented PDF exploration workspaces

agent-rip-docling

Offline, agent-oriented document exploration workspaces

bragi-io

Python SDK for Bragi — parse PDFs into typed semantic document graphs

crewai-xberg

Xberg document extraction tools for CrewAI agents — text, metadata, and batch extraction across 107 file formats

google-drive-storage-local

PyPI Package for Circles google-drive--storage-local Python

html-reader-llm

HTML simplification and intelligent extraction for LLM

langchain-docuweave

An integration package connecting DocuWeave and LangChain.

langchain-opendma

Integration of Enterprise Content Management (ECM) systems with LangChain through toolkits, loaders, and retrievers

langchain-unstructured-transform

LangChain tools for the Unstructured Transform MCP server: parse, enrich, chunk, and embed files for RAG and AI pipelines.

langchain-xberg

LangChain document loader for Xberg — extract 88+ file formats into Documents with async, batching, chunking, and rich metadata

llama-index-node-parser-xberg

Structure-aware LlamaIndex node parser that turns xberg native chunks and elements into nodes

llama-index-readers-feishu

LlamaIndex data loaders for Feishu/Lark wiki, docs, and drive

More in Data, search & knowledge