Data, search & knowledge

Document processing & OCR

1,074 agents · most starred first

Document processing & OCR, page 5 of 11

smartpipe★ 5

Semantic pipes for your terminal - PDFs, images, audio, video, and text through Unix verbs that understand

microsoft-foundry-content-understanding-cuad-benchmark★ 5

Benchmark Microsoft Foundry Content Understanding on CUAD legal contracts. Achieves 83.3% F1 score (29% better than GPT-4o baseline). Complete Python notebook with optimized schemas for contract clause extraction. Production-ready with confidence scores & cost analysis.

pretext-pdf★ 5

Generate PDFs from JSON — declarative, serverless, no Chromium. TypeScript-first with professional typography.

MarkItDown★ 5

C#/.NET port of Microsoft's MarkItDown Python library — a converter-driven pipeline that turns virtually any document or URL into clean Markdown.

DOREA-X★ 5

문서 이해부터 보고서 작성까지 전 과정을 함께하는 문서 작업 AI 에이전트 — PDF·HWP·Office 분석, RAG 대화, 보고서 작성. 한 줄 설치 배포판(DOREA-XP) 포함. Document-centric AI agent for reading, RAG chat, and report writing.

pdf-pilot★ 5

智能PDF转换器,可针对每种文档类型自动选择最佳引擎(Docling/MinerU/PyMuPDF4LLM)。无需任何配置即可获得最佳的Markdown和Word输出效果。

PDF-AI-Viewer★ 5

PyQT6开发的PDF论文阅读/翻译/AI总结小工具(仿知云) Vibe Coding作品

figure-extractor★ 5

Extract complete, reviewable figures and tables from PDF, arXiv, and HTML papers — an installable AI-agent skill and CLI with contact-sheet QA.

marksentry★ 5

Secure, local-first document-to-Markdown conversion. Zero-trust input sanitization, multi-column PDF layout, LaTeX math, PII masking. No cloud dependencies.

distillr★ 5

Turn YouTube, websites, and arXiv papers into a structured, reusable corpus of insights, syntheses, and reports.

PFS★ 5

Precision File Search (PFS) is an AI-powered desktop file search for finding, classifying, and understanding files. Search by keyword and semantics inside files, ask questions, and quickly gain insights from cluttered and scattered documents.

acessilia★ 5

Agentic Al platform for document understanding, structural extraction and accessibility transformation.

Construction-PDF-Validation-AI★ 5

AI-powered document intelligence pipeline for technical drawing compliance. Combines PDF parsing, OCR, multimodal vision analysis, FAISS RAG retrieval, and deterministic rule validation to audit engineering documents against technical specifications using a fully local Ollama-based stack.

docai★ 5

Local-first OCR → Markdown → RAG toolkit with optional Hugging Face/custom endpoints. Tk UI for viewing, OCR-ing, and chatting with PDFs; Docker/pyproject ready; pluggable OCR/embeddings/LLM.

sortex-ai★ 5

Production-grade AI platform for automating logistics document processing with OCR, LLMs, validation workflows, and human-in-the-loop review.

bruce-md2word★ 5

面向 AI Agent 的 Markdown 转 Word 工具:中文排版、Mermaid 图表、可编辑数学公式,提供 Skill、独立 CLI 和 DSH 插件。

docai-analysis-platform★ 4

Intelligent Document Analysis Platform. Processes 100-page PDFs in 30 seconds, Answers questions with 90%+ accuracy and supports multiple AI models with intelligent fallback

Invoice-extractor★ 4

Streamlit app leveraging OpenAI's LLM for accurate invoice extraction, supporting PDF files and offering JSON/CSV outputs.

arcnem-vision★ 4

An AI-powered platform for document ingestion, processing, and similarity search

verbify★ 4

Powered NLP with LLMs

ai-document-data-extraction-evaluation★ 4

This project demonstrates how to evaluate the use of LLMs and SLMs for extracting structured data from documents using .NET

Extracto★ 4

Your private document brain. PDFs in, RAG out. Self-hosted. Plug everywhere.

docnest★ 4

The document normalization engine RAG has always needed. Parse any document, understand its structure, build RAG that actually works.

langparse★ 4

LangParse is a universal document parsing and text chunking engine for LLM or Agent applications — Documents In, Knowledge Out.

lazy-AI-txt-tool★ 4

Simple GUI with some python scripts I use to convert folders to single txt output for AI data dumping

FileFlow★ 4

一款AI驱动的本地文件分类工具,支持文档解析、多级自动分类和自然语言搜索,适合学生和职场人士管理大量文件 ( An AI-powered local file classification tool that supports document parsing, multi-level auto-categorization, and natural language search, ideal for students and office workers managing large volumes of files)

stripe_docs_markdown★ 4

An offline-first, LLM-optimized collection of the entire Stripe API documentation. Every endpoint, every object, and every guide — organized and ready for your next project.

datalab-cli★ 4

Convert, extract, and process documents from the command line

Agentic-Document-Extraction-PDF★ 4

An agentic, zero‑shot document intelligence engine that sees, understands, and extracts from any PDF, no training, no hallucinations. Just define your fields and get trusted, structured outputs with confidence scores, deployed locally and built for the enterprise.

memtruth★ 4

Memtruth SDK: evidence, parse, corpus contracts, chunking, projection, and diagnostics for AI applications.

extractflow★ 4

Reliable, schema-validated structured extraction from documents (PDF, DOCX, CSV, email) using LLMs — built for automation pipelines.

fillform★ 4

Evidence-based document extraction API for form filling. Local-first (Ollama), also supports OpenAI-compatible endpoints and Claude.

text-splitter★ 4

Split and analyze text files

docling-skill★ 4

Agent-first document ingestion layer on Docling with Markdown, image sidecars, manifests, OCR, and quality gating.

awaitverify-managed-document-verification-pdf-ocr-extraction★ 4

Send your low-confidence document extractions. A human reviews them against the PDF and returns a typed Pydantic/Zod response. Managed document verification for AI agents. PDF + handwritten OCR. Client-side fragmentation: full document never leaves your machine. $0.80/page + $5 free credit. Express 30-min SLA. Built on open source awaithumans.

extract_text_from_image★ 4

streamlit region:us

PaddleDoc★ 4

Document OCR and Markdown extraction pipeline built on PaddleOCR, designed to feed RAG systems.

pdf-inspector-web-ui★ 4

Zero-dependency browser UI for pdf-inspector (Firecrawl) — parse PDFs to structured Markdown entirely client-side via WebAssembly. Written in Rust.

FileCollector★ 4

GTK4 / libadwaita file collector for LLMs — tick files in a project tree and merge them into one TXT, with project and phrase management

ocr_genAI★ 4

This Python package allows you to perform OCR on images using Tesseract and interpret the results using generative AI models like OpenAI's GPT ,Anthropic's claude and Google's Gemini.

LlamaParse★ 4

C# SDK for the LlamaParse API -- document parsing, extraction, RAG pipelines, and file management

CAD-pdf-chatbot★ 4

Upload a CAD PDF to extract text and automatically generate a concise engineering summary using a local LLM.

AI-OCR★ 4

Advanced AI-OCR with FastAPI and OpenAI Integration

PDFimageText_Extraction-Zpdf★ 4

基于微调大语言模型的智能文档处理平台,将PDF以高精度转换为Markdown格式,对包含LaTex公式、学术图表、化学分子式的科技文档、学术论文具有卓越表现。

AIDocSynth★ 4

AIDocSynth liest Dokumente (direkt + OCR), analysiert Inhalte mithilfe von KI und legt jede Datei – PDF, Bild oder Office-Dokument – deterministisch in einem passenden Ordner ab. Versionierung sowie reichhaltige Metadaten sind integriert.

legal_data_mining★ 4

Flujo reproducible en Google Colab y como script Python para minería de “fichas” de jurisprudencia: limpieza y normalización de textos, generación de embeddings con OpenAI (main) y BERT (branch), agrupación mediante clustering, perfilado de clusters y generación automatizada de insights vía llamadas a LLM.

evb-viewer★ 4

Scanned-document workbench that AI agents can operate: clean, OCR, annotate PDF and DjVu, with a local MCP server. macOS, Windows, Linux, Web.

doc-audit-ai★ 4

DocAudit AI is an intelligent, Next.js-powered SaaS application that leverages Google Gemini 2.5 Flash to automatically audit, summarize, and extract risk factors from financial and legal PDF documents.

nexus-pdf-editor★ 4

In-browser PDF text editor with AI redaction agent — click to edit, export clean PDFs

quizforge★ 4

题库 PDF 进 · 随机抽题出 —— 非结构化题库 PDF 的结构化抽取 + 智能刷题系统(规则优先 + LLM 兜底 / 三池加权抽题 / Leitner 间隔重复 / 带引用讲解)

DocFailBench★ 4

Failure-oriented benchmark for PDF-to-Markdown, OCR, and VLM document parsers with executable assertions and public release leaderboards.

DocMarrow★ 4

Pure TypeScript document parser for PDF → Markdown, JSON and RAG chunks.

docgrain★ 4

Document-to-knowledge engine: normalizes PDF, DOCX, XLSX, TXT and images into one versioned, source-linked model that AI assistants, apps and websites can use.

vidlens★ 4

为 AI Agent 准备多模态视频证据:抖音/B站转写、自适应取帧、时间线素材包;支持 Windows、macOS 与 Linux。

Evidence-Chunker★ 4

A Python library that increases RAG accuracy by grouping tables, captions, and text paragraphs from Docling-parsed PDFs into a single Evidence Unit.

LLM-pdf-extraction★ 3

This project provides an API for uploading PDF documents and extracting structured summaries using either OpenAI's GPT-4o or Anthropic's Claude models. It is optimized for environmental and agricultural reports, transforming unstructured PDF content into structured JSON for downstream use.

graphscribe-table-extractor★ 3

Graphscribe is an intelligent, LLM-powered document understanding system designed to extract structured insights from complex visual content such as statistical diagrams, charts, and graphs.

Document-processing-Pdf-Structured-Data-Extractor★ 3

This project demonstrates how to extract structured information from PDF documents using a combination of Langchain, OpenAI models, and the DocLing library. It provides a framework for parsing PDFs and leveraging LLMs to identify and format key data points.

essay-auto-analysis★ 3

论文自动化分析工具

MCP_Document_Classifer★ 3

An intelligent document processing system that uses the Model Context Protocol (MCP) to extract, analyze, and route business documents automatically

omnivec★ 3

Analyze ZIPs of documents and images, detect duplicates and similarity clusters locally, and generate curation reports through a simple API

ctx★ 3

CTX (Context Transfer Format) — universal interchange format for LLM web content consumption

markitdown-for-ai★ 3

MarkItDown is a Python tool that converts various document formats to Markdown. This Docker image provides a portable, easy-to-use containerized version that works out of the box.

ai-json-cleanroom★ 3

Automatically extracts JSON from markdown/text, repairs common AI mistakes, validates structure. Returns clean data when successful, detailed feedback for retries when not.

multi-modal-rag★ 3

Multi-Modal RAG: An AI-powered pipeline for extracting, chunking, and summarizing content from PDF documents using advanced chunking strategies and generative models. Includes support for text, tables, and images, with vector search and retrieval via ChromaDB.

DocuChat_AI★ 3

AI document intelligence assistant with RAG, OCR, NER, document classification, source-cited Q&A, risk detection, and evaluation metrics for PDFs, DOCX, TXT, and scanned documents.

reczipes★ 3

AI-powered recipe extraction using Apple Vision OCR and LLM reasoning. Converts photos of recipes into structured data with allergen and FODMAP analysis.

pdf_explainer★ 3

gradio agent-demo-track region:us

github-pdf-converter★ 3

gradio region:us

OCR_with_LLMs★ 3

gradio region:us

Automated_LLM_data_parsing_system★ 3

gradio region:us

smart_reader★ 3

Desktop AI assistant for reading and interpreting technical report/standards/regulation PDFs with local rendering and agent tools, also a light weight and high efficient PDF viewer.

dsh-ocr-skill★ 3

把 PDF/Word/PPT/Excel 与图片转成结构干净的 Markdown,表格保留行列(DocMark API)。用于文档解析、批量入库 RAG/知识库、扫描件与发票/证件/图片/订单截图 OCR;需 DOCMARK_API_KEY 付费模式,不支持 .json/.html。

pagemark★ 3

PDF to Markdown with vision-language models — bring your own OpenAI-compatible endpoint. Detects and recovers from VLM failures instead of passing them through.

ImageOCR★ 2

Software to index images based on their text content for easy search, search words the screenshot or image contains.

anyparser_crewai★ 2

Supercharge your AI workflows by combining Anyparser’s advanced content extraction with Crew AI. With this integration, you can effortlessly leverage Anyparser’s document processing and data extraction tools within your Crew AI applications.

GEHD★ 2

基于规则+LLM+搜索三层管道的文档幻觉核查工具

shipressure★ 2

Turn PDFs, Docs, Excel files, websites and GitHub repos into AI-ready compressed context for Claude Code, Codex, Gemini CLI and AI Agents.

MarkPdfDown★ 2

Convert PDF pages to Markdown using an ASP.NET Core API backed by Azure OpenAI.

lmb-chats2md-gpt★ 2

Python tool to convert ChatGPT conversation exports (JSON) to organized Markdown files with metadata and deduplication.

Document_Comparison_with_Agents★ 2

streamlit region:us

Metadata_Generator_Agent★ 2

streamlit region:us

pdf-intelligence-assistant★ 2

docker region:us

ocr-LLM-image-summarizer★ 2

streamlit region:us

agentic-doc-sim-streamlit★ 2

docker region:us

Document-AI-GPT★ 2

gradio region:us

LLM_Florence_Handwriting_Reader★ 2

gradio mcp-server region:us

PareseKit★ 2

Menu-bar app: PDFs, Office & images → clean Markdown on your Mac. Offline, local, no API keys.

decant★ 2

Get the benefits of pre-converting to markdown without interrupting your workflow. Pour a document into a lighter, cleaner form and leave the heavy sediment (the image layer) behind before it reaches the LLM.

locallens★ 2

Local OCR for DeepSeek Harness — read text from screenshots on your Mac with Apple's Vision framework. No API key, no upload.

ebook2md★ 2

Convert EPUB, PDF, FB2, and DJVU to Markdown — pre-process ebooks for LLMs and save tokens

wikidoc★ 2

Sort your documents into a corpus you can query — a filing skill for Claude Code

gander★ 2

Understand a local media file (image/video/audio) from the command line — transcript + structured description as one JSON envelope, via an agentic CLI backend (agy/claude/codex).

Fily★ 2

Local-first macOS app that indexes your files and builds an AI-organized virtual folder tree without moving or renaming originals.

reel-ripper★ 2

Turn Instagram reels into local transcripts, keyframes, and LLM-ready Markdown bundles.

OCRtist★ 2

基于 Qwen3-VL 多模态大模型的中文票据 OCR 智能体:识别 → 校验 → 纠错 → 进化的多阶段 Agent 闭环流水线,配置驱动支持发票、身份证等多种票种

doc-to-md★ 2

Agent Skill:文档/表格先转 Markdown 再读(MinerU 4.x;Windows + Unix 脚本)

parsekit★ 2

Menu-bar app: PDFs, Office & images → clean Markdown on your Mac. Offline, local, no API keys.

refman★ 2

Agentic Reference Manager and PDF annotation tool

pdfops★ 2

Fast PDF tools for AI agents: 31 tools in one Rust binary. CLI, MCP server and library.

More in Data, search & knowledge