document-ai repositories
Trending repositories tagged document-ai, ranked by trending score. Updated daily.
-
1
FB208/OpenBidKit_Yibiao
开箱即用的AI标书编写工具,标书AI生成工具,投标工具箱、知识库、标书查重、废标项检查,完全开源免费,欢迎使用
GitHub · JavaScript · 3,363 stars · 873 forks · +32 stars in 24 hours · Trending score 2.93
-
2
datalab-to/surya
OCR, layout analysis, reading order, table recognition in 90+ languages
GitHub · Python · 21,605 stars · 1,569 forks · +7 stars in 24 hours · Trending score 2.64
-
3
xerrors/Yuxi
可私有部署的多租户知识智能体平台:统一 RAG、知识图谱、多智能体、MCP/Skills、沙盒与权限管理。Yuxi = Cloud Agents + Knowledge RAG, Self-hosted knowledge agent platform for RAG, knowledge graphs and multi-agent workflows.
GitHub · Python · 7,696 stars · 1,275 forks · +4 stars in 24 hours · Trending score 2.01
-
4
run-llama/ParseBench
ParseBench - A Document Parsing Benchmark for AI Agents
GitHub · Python · 648 stars · 140 forks · +5 stars in 24 hours · Trending score 1.76
-
5
RISE-UNIBAS/humanities_data_benchmark
LLM Benchmark Suite for Humanities Data
GitHub · Python · 34 stars · 8 forks · +3 stars in 24 hours · Trending score 1.10
-
6
Zipstack/unstract
LLM-Driven Extraction of Unstructured Data — Built for API Deployments & ETL Pipeline Workflows
GitHub · Python · 7,460 stars · 760 forks · 0 stars in 24 hours · Trending score 0.93
-
7
AI-WorkDeck/aiworkdeck
Open-source AI workspace for legal document work: reviewable AI edits as tracked changes, linked sources, project history. Desktop app + plugin SDK. 开源法律 AI 文档工作台
GitHub · JavaScript · 187 stars · 25 forks · 0 stars in 24 hours · Trending score 0.83
-
8
NameetP/pdfmux
PDF extraction that audits its own output — and certifies any other extractor's, catching pages they silently dropped. Verify signed manifests offline: free, MIT, no account. 0.903 on opendataloader-bench, #2 of 8 engines. 7-tool MCP server.
GitHub · Python · 87 stars · 15 forks · +1 stars in 24 hours · Trending score 0.65
-
9
zhihengli-casia/PureDocBench
PureDocBench: source-traceable benchmark for document parsing across clean, degraded, and real-world settings
GitHub · Python · 52 stars · 1 forks · +1 stars in 24 hours · Trending score 0.45
-
10
ggozad/haiku.rag
Agentic RAG for local and self-hosted document search: hybrid retrieval, reranking and multimodal RAG on embedded LanceDB, with Docling parsing and an MCP server
GitHub · Python · 659 stars · 60 forks · 0 stars in 24 hours · Trending score 0.42
-
11
arpitpatel25/ReadAnyDoc
Open-source Reducto alternative: parse PDFs, scans and forms into Markdown, tables and typed data with a citation for every value. Claude Haiku or any model. Python library, MCP server, Reducto-compatible API.
GitHub · Python · 11 stars · 3 forks · +1 stars in 24 hours · Trending score 0.42
-
12
harumiWeb/exstruct
Conversion from Excel to structured JSON (tables, shapes, charts) for LLM/RAG pipelines, and autonomous Excel reading/writing by AI agents via CLI and MCP integration.
GitHub · Python · 203 stars · 31 forks · 0 stars in 24 hours · Trending score 0.36
-
13
cernodatainc/cernodata
Open-source control layer over PDF parsing that picks the right method, verifies output quality, and falls back automatically when results fall short
GitHub · Python · 24 stars · 6 forks · 0 stars in 24 hours · Trending score 0.30
-
14
eulogik/TinyDoc-VLM
256M-param document VLM: SigLIP + SmolLM2. LoRA fine-tuning, ONNX export, runs on CPU. Apache 2.0.
GitHub · Python · 11 stars · 0 forks · 0 stars in 24 hours · Trending score 0.21
-
15
MartinsMessias/rasgapdf
Blazing-fast 2D Spatial PDF Parser in Pure Rust (Python, Node.js, Go, C#). Extract exact [x0, y0, x1, y1] bounding boxes, text blocks, tables, images & vector paths in ~3-8ms/page for RAG & LLMs.
GitHub · Rust · 21 stars · 1 forks · 0 stars in 24 hours · Trending score 0.19
-
16
Yonagi043/vestigium
Every answer leaves a trace back to its page. An MCP server that lets AI agents read long PDFs by address and cite the pages.
GitHub · Python · 13 stars · 0 forks · 0 stars in 24 hours · Trending score 0.14
-
17
Gunnarguy/OpenIntelligence
Apple-native iOS/macOS app for document intelligence, OCR, cited answers, and source-backed retrieval over PDFs, scans, and user-controlled files.
GitHub · Swift · 30 stars · 4 forks · 0 stars in 24 hours · Trending score 0.10
-
18
dkylewillis/vera
GitHub · Python · 18 stars · 1 forks · 0 stars in 24 hours · Trending score 0.09
-
19
AkshatTm/Vidura-IPO-X-Ray
Vidura reads an Indian IPO offer document (RHP/DRHP) on your own machine and returns a report you can check: key facts with page citations, 13 red-flag checks, plain-English risk factors, a reasoned risk level and a chat that verifies every number. Open-weight models only. Not investment advice.
GitHub · Python · 9 stars · 0 forks · 0 stars in 24 hours · Trending score 0.05
-
20
shcherbak-ai/contextgem
Extract structured data and insights from documents using LLMs and decision models
GitHub · Python · 2,080 stars · 191 forks · 0 stars in 24 hours · Trending score 0.03
-
21
wxyhgk/retain-pdf
在保留版面、公式与结构的前提下进行 PDF 翻译,适用于科研与技术文档
GitHub · Python · 2,632 stars · 294 forks · 0 stars in 24 hours · Trending score 0.00
-
22
CHEN010325/paddleocr-local
Local-first document parsing workbench for five OCR models: PDF/Office to Markdown with WebUI, model switching, CLI and Apple Silicon support.
GitHub · Python · 138 stars · 32 forks · 0 stars in 24 hours · Trending score 0.00
-
23
web-dienste/AI-Paperless-Organizer
AI-powered companion for Paperless-ngx: auto-classify documents, merge duplicate tags & correspondents, re-OCR with local vision models, chat with your archive (RAG), import from cloud drives and detect duplicates. Runs fully local with Ollama.
GitHub · TypeScript · 17 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00
-
24
I3K-IT/RAG-Enterprise
🚀 100% local RAG system with one-command setup. Your data never leaves your server.
GitHub · Rust · 59 stars · 10 forks · 0 stars in 24 hours · Trending score 0.00