Açık kaynak radarı

Havuz

Takip ettiğimiz konularda yükselen açık kaynak projeler — yıldız ivmesi, gerçek geliştirme aktivitesi ve AI değerlendirmesiyle.

repo · sayfa 1 / 1

Sırala

Yıldız/gün (hız)Son gün (★/gün)Son hafta (★/gün)Son ay (★/gün)Toplam yıldız AI önem skoru Bana uyum Commit (28g)Yazar (28g)En yeni

Konu

Tümü AI / LLM18 Veri9 Geliştirici araçları13 Diğer3 SaaS altyapı13 Web11

Süz

Yalnız hareketli Yalnız analizli≥ 0 ≥ 100 ≥ 500 ≥ 2.000

Yalnız hareketli, son 28 günde commit almamış repoları gizler (yıldızı olan ama bırakılmış projeler). Commit sayısı henüz ölçülmemiş repolar da gizlenir.

EtiketTüm GitHub etiketleri — repo sahiplerinin koyduğu topic'lergöster

Sırala:

Etiketler yükleniyor…

Aktif document-parsing

1
aiptimizer/TurboOCR 1.152
TurboOCR, >200 img/s OmnidocBench. TensorRT FP16, PP-OCRv6, HTTP + gRPC
5,1/gün ort. +1 son gün 0 commit 0 yazar C++ 20 Mar 2026 güncellendi 27 Eyl 2026
document-parsing fastapi fp16 grpc ocr paddleocr pdf-extraction rag
1.152
2
FengZhenfei/carrel 703
Ontology-Augmented Generation for AI agents.
19,5/gün ort. +22 son gün 32 commit 1 yazar Python 28 Eyl 2026 güncellendi dün
agent-skills document-parsing knowledge-graph mineru neo4j ontology opensearch qdrant
703
3
run-llama/ParseBench 625
ParseBench - A Document Parsing Benchmark for AI Agents
3/gün ort. +5 son gün 98 commit 10 yazar Python 10 Nis 2026 güncellendi dün
benchmark document-ai document-parsing evaluation llamaindex llm machine-learning ocr
625
4
LeDat98/NexusRAG 528
Hybrid RAG system combining vector search, knowledge graph (LightRAG), and cross-encoder reranking — with Docling document parsing, visual i
2,3/gün ort. +0 son gün 0 commit 0 yazar Python 15 Mar 2026 güncellendi 20 Nis 2026
chromadb citation docling document-parsing fastapi gemini knowledge-base knowledge-graph
528
5
YOLOW92/pagesift 187
Rust web scraper & crawler for AI agents: URLs, PDFs and Office files → clean Markdown/JSON. Firecrawl- and Jina Reader-compatible API, MCP
13,4/gün ort. +3 son gün 459 commit 2 yazar Rust 20 Eki 2026 güncellendi dün
ai-agents browser-automation data-extraction firecrawl html-to-markdown markdown mcp pdf-extraction
187
6
ComPDFKit/docslight 137
With DocSlight, precisely parse and extract data from any document, including PDFs, scans, images, and Office files. It is an open-source AI
1,1/gün ort. +1 son gün — commit Vue 30 Haz 2026 güncellendi 19 gün önce
document-data document-information-extraction document-parser document-parsing docx-to-json extraction image-parser image-to-json
137
7
arthurpanhku/DocSentinel 89
MCP server for AI agent for cybersecurity: automate assessment of documents, questionnaires & reports. Multi-format parsing, RAG knowledge b
0,4/gün ort. +0 son gün — commit Python 06 Mar 2026 güncellendi 7 gün önce
ai-agent compliance document-parsing fastapi llm ollama openai rag
89
8
unitedrhino/docling 70
Get your documents ready for gen AI, in pure Go. A Go alternative to anydoc & Docling — 纯 Go 实现的文档解析库:PDF/Word/PPT/Excel/HTML/Markdown/EML/图
1,3/gün ort. +1 son gün — commit Go 11 Eyl 2026 güncellendi 21 gün önce
ai anydoc docling document-parser document-parsing docx go golang
70
9
InternLM/Visual-ERM 68
[NeurIPS 2026] Official Implementation of "Visual-ERM: Reward Modeling for Visual Equivalence"
0,3/gün ort. +0 son gün — commit Python 09 Mar 2026 güncellendi 23 Mar 2026
chart-understanding document-parsing large-language-models large-vision-language-models llm reward-model svg-generation vision-langauge-model
68
10
ComPDF-derek/docslight 52
Part of the KDAN ecosystem, DocSlight offers document parsing, OCR, and data extraction that turn PDFs, scans, images, and Office files into
0,4/gün ort. +0 son gün — commit Vue 09 Tem 2026 güncellendi 31 Tem 2026
document-data-extraction document-information-extraction document-parser document-parsing docx-to-json image-parser image-to-json intelligent-document-processing-open-source
52
11
zhihengli-casia/PureDocBench 50
PureDocBench: source-traceable benchmark for document parsing across clean, degraded, and real-world settings
0,3/gün ort. +1 son gün — commit Python 08 May 2026 güncellendi 7 gün önce
benchmark document-ai document-parsing ocr synthetic-data
50
12
janderswag/docuchat.app 37
Private, self-hosted document chat for attorneys: parse legal PDFs and query them with local open-source LLMs (Ollama) + verifiable page cit
0,3/gün ort. +0 son gün — commit Python 22 Haz 2026 güncellendi 22 Tem 2026
chat-with-pdf citations desktop-app document-chat document-parsing fastapi lancedb legal-ai
37
13
DocSlicer/DocSlicer 36
Fast, deterministic document parser and chunker for RAG and agent pipelines. Ships an MCP server for agents navigating long documents with p
0,2/gün ort. +0 son gün — commit Python 17 Mar 2026 güncellendi 02 Eyl 2026
agent-harness chunking document-analysis document-parsing docx html llm markdown
36
14
ENDEVSOLS/LongParser 30
Privacy-first document intelligence engine — parse PDFs, DOCX, PPTX, XLSX & CSV into AI-ready chunks for RAG pipelines. Includes HITL review
0,1/gün ort. +0 son gün — commit Python 04 Nis 2026 güncellendi 12 gün önce
chunking docling document-intelligence document-parsing fastapi human-in-the-loop langchain llm
30
15
ryanmeowy/anchr-docling 25
Async Docling sidecar that turns PDFs and office documents into Markdown, text, structured blocks, chunks, and extracted images for RAG. Pyt
0,2/gün ort. +0 son gün — commit Python 25 May 2026 güncellendi 20 gün önce
chunking docling document-ai document-conversion document-parsing fastapi markdown ocr
25
16
F2-AI-Inc/docray 23
X-ray for documents: lossless PDF & PPTX extraction to JSON with bounding boxes, fonts, and colors — CLI, HTTP API, and an in-browser playgr
0,2/gün ort. +0 son gün — commit HTML 14 Tem 2026 güncellendi 5 gün önce
bounding-boxes document-parsing json llm pdf pdf-extraction pdfium powerpoint
23
17
Yurzi/dsh-pdf-mineru 22
Provider-independent DSH PDF reading tool powered by MinerU.
0,3/gün ort. +0 son gün — commit TypeScript 24 Ağu 2026 güncellendi 9 gün önce
deepseek-harness document-parsing dsh-plugin mineru ocr pdf typescript
22
18
cernodatainc/cernodata 21
Open-source control layer over PDF parsing that picks the right method, verifies output quality, and falls back automatically when results f
0,3/gün ort. +0 son gün — commit Python 15 Ağu 2026 güncellendi 2 gün önce
data-extraction data-ingestion data-pipelines data-quality document-ai document-parser document-parsing layout-analysis
21
19
kreuzberg-dev/kreuzberg-lts 21
Kreuzberg v4 LTS — long-term support for the v4 line (legacy; superseded by xberg for v5+). MIT-licensed.
0,2/gün ort. +0 son gün — commit Rust 10 Tem 2026 güncellendi 4 gün önce
data-extraction document-intelligence document-parsing docx lts ocr pdf pdf-extraction
21
20
Sqhao-O/dsh-docs 16
Fully local document intelligence for DeepSeek Harness. Parse PDF, Office files, images, and scanned documents with offline OCR. | DeepSeek
0,2/gün ort. +0 son gün — commit TypeScript 14 Ağu 2026 güncellendi 19 gün önce
ai-agent deepseek deepseek-harness docling document-intelligence document-parsing document-processing dsh-plugin
16
21
caichuanwang/OpenDocs 15
Convert local documents (PDF, DOCX, PPTX, images, TXT, Markdown) to clean Markdown with optional LLM vision — Python SDK
0,2/gün ort. +0 son gün — commit Python 27 Tem 2026 güncellendi 21 Ağu 2026
document-conversion document-parsing docx llm markdown pdf pptx python
15
22
buptanswer/mineru 14
让 MinerU 在 AMD 显卡上以 vLLM + hybrid-auto-engine 满血运行！本项目是对官方文档中 AMD/ROCm 生态支持的有效补充。针对 MinerU 3.x 提供了一套完整的 ROCm 7.x + PyTorch 2.11.0 + vLLM 源码
0,1/gün ort. +0 son gün — commit Python 25 May 2026 güncellendi 27 May 2026
amd-gpu data-extraction document-parsing e-book llm mineru python pytorch
14
23
hwdsl2/parsecrate 14
ParseCrate: self-hosted document processing API powered by Docling and docling-serve. Converts PDF, DOCX, PPTX, HTML, and more to Markdown/J
0,1/gün ort. +0 son gün — commit Jupyter Notebook 11 May 2026 güncellendi 2 gün önce
ai cuda deep-learning docker docker-compose docker-image docling document-conversion
14