Footer

Your go-to destination for discovering trending open-source projects and uncovering the insights that matter

Legal

  • Terms and conditions
  • Privacy policy

More

  • Pricing
  • Advertise
  • onedump
  • gosnakego
  • Contact us

Social

  • X (Twitter)
  • GitHub
Trendshift owl
What they build speaks louder than words
© 2026 Trendshift, created by Julian Li with ❤️
SignalAdvertise
Trendshift
SignalAdvertise
Sign in
Trendshift owl

Discover trends that matter

SignalAdvertise
DailyWeeklyMonthlyYearly
Live mentionsTopics
RepositoriesDevelopers
InsightsStats
Busbar
Busbar
Bifrost
Bifrost
Omnigraph
Omnigraph
Websitebench
Websitebench

opendataloader-project/opendataloader-pdf

PDF Parser for AI-ready data. Automate PDF accessibility. Open-source.

#Document parsing
Visit GitHub
Java
30.3k
3k
30 contributors
Apache License 2.0
website
AchievementsView all →
FeaturedAdvertise to 180K+ monthly visitors
Busbar

Control what AI can do before it acts

Bifrost

Fastest Enterprise AI Gateway for Routing, Governing, and Securing all your AI Traffic

Omnigraph

Versioned graph database on object storage. Git-style workflows and multimodal retrieval

Websitebench

Can AI agents reverse-engineer real websites?

Momentum

How fast opendataloader-project/opendataloader-pdf is gaining stars, and where it lands on Trendshift and GitHub Trending

Activity and trending

Stars, forks and merged pull requests each day or month, lined up with the repository's rank on Trendshift Trending

Sep 11 – Nov 10, 2026

Stars +1,198 in 61 days

0100200
160

Forks +162 in 61 days

0102030
25

Merged PRs 130 in 61 days

01020
16

Trendshift Trendingwhere the repository ranked each day it made the top 25

Top 25 in Java

5474106748201615
Sep 11Sep 19Sep 27Oct 5Oct 13Oct 21Oct 29Nov 6
The left and right arrow keys step from day to day; Home and End go to the first and the last

Stars, forks, merged pull requests and Trendshift Trending rank, by day
DayStars gainedForks gainedMerged PRsJava
Fri, Sep 11, 2026+13+20Not trending
Sat, Sep 12, 2026+16+20Not trending
Sun, Sep 13, 2026+52+50#5
Mon, Sep 14, 2026+24+32Not trending
Tue, Sep 15, 2026+64+00#4
Wed, Sep 16, 2026+53+51#7
Thu, Sep 17, 2026+11+24Not trending
Fri, Sep 18, 2026+6+11Not trending
Sat, Sep 19, 2026+2+00Not trending
Sun, Sep 20, 2026+7+10Not trending
Mon, Sep 21, 2026+14+21Not trending
Tue, Sep 22, 2026+10+43Not trending
Wed, Sep 23, 2026+13+30Not trending
Thu, Sep 24, 2026+4+10Not trending
Fri, Sep 25, 2026+10+20Not trending
Sat, Sep 26, 2026+10+10Not trending
Sun, Sep 27, 2026+2+00Not trending
Mon, Sep 28, 2026+6+13Not trending
Tue, Sep 29, 2026+15+20Not trending
Wed, Sep 30, 2026+38+53#4
Thu, Oct 1, 2026+10+03Not trending
Fri, Oct 2, 2026+0+30Not trending
Sat, Oct 3, 2026+8+30Not trending
Sun, Oct 4, 2026+26+50#10
Mon, Oct 5, 2026+0+11Not trending
Tue, Oct 6, 2026+0+10Not trending
Wed, Oct 7, 2026+13+10Not trending
Thu, Oct 8, 2026+9+10Not trending
Fri, Oct 9, 2026+11+30Not trending
Sat, Oct 10, 2026+7+10Not trending
Sun, Oct 11, 2026+86+60#6
Mon, Oct 12, 2026+52+24#7
Tue, Oct 13, 2026+25+26Not trending
Wed, Oct 14, 2026+21+31Not trending
Thu, Oct 15, 2026+12+24Not trending
Fri, Oct 16, 2026+14+47Not trending
Sat, Oct 17, 2026+3+00Not trending
Sun, Oct 18, 2026+9+10Not trending
Mon, Oct 19, 2026+7+02Not trending
Tue, Oct 20, 2026+2+04Not trending
Wed, Oct 21, 2026+8+25Not trending
Thu, Oct 22, 2026+160+254#4
Fri, Oct 23, 2026+59+111#8
Sat, Oct 24, 2026+6+10Not trending
Sun, Oct 25, 2026+19+30Not trending
Mon, Oct 26, 2026+42+83#20
Tue, Oct 27, 2026+25+28Not trending
Wed, Oct 28, 2026+39+82#16
Thu, Oct 29, 2026+11+25Not trending
Fri, Oct 30, 2026+7+116Not trending
Sat, Oct 31, 2026+5+00Not trending
Sun, Nov 1, 2026+7+21Not trending
Mon, Nov 2, 2026+18+15Not trending
Tue, Nov 3, 2026+8+16Not trending
Wed, Nov 4, 2026+2+16Not trending
Thu, Nov 5, 2026+12+19Not trending
Fri, Nov 6, 2026+9+29Not trending
Sat, Nov 7, 2026+22+50#15
Sun, Nov 8, 2026+38+40Not trending
Mon, Nov 9, 2026+15+10Not trending
Tue, Nov 10, 2026+1+00Not trending
Total+1,198+162130
  • 1#1 on the list
  • 7Rank that day
  • Not trending
1

    • GitHub trending history

    Where the repository ranked on GitHub Trending, one dot for each day it was on a list

    Mar 19 – Jun 3, 2026#1 on 1 day

    #1#5#10#15#20#25
    Top 10
    Apr 2026MayJunJulAugSepOctNov
    The left and right arrow keys step from day to day; Home and End go to the first and the last

    Mentions and achievements

    Where people are talking about opendataloader-project/opendataloader-pdf, and every badge it has earned
    1. Nov 51 post

      • 🚨 Some guy just open-sourced a tool that converts pdfs to markdown at 100 pages per second. It's called OpenDataLoader. It runs entirely on CPU and handles complex layouts, tables, and nested…

        Read full on X, posted by @mdancho84

        @mdancho84 · x.com

    2. Oct 301 post

      • PDF、Word 直接丢给 AI，表格乱、标题丢、token 白烧。先转成 Markdown 再喂。下面 5 个开源工具，按文件类型挑，建议先收藏： 1. MarkItDown（微软开源，MIT） Word、Excel、PPT、PDF 都能转成 Markdown，办公文档先试它。 pip install 'markitdown[all]' 2. Docling（代码 MIT） 复杂 PDF…

        Read full on X, posted by @LRuibiao69297

        @LRuibiao69297 · x.com

    3. 18 days earlier
    4. Oct 121 post

      • This open-source tool converts PDFs to Markdown at over 100 pages per second on CPU. It’s called OpenDataLoader PDF. - Exports Markdown, JSON, and HTML - Preserves headings, lists, and reading order…

        Read full on X, posted by @simplifyinAI

        @simplifyinAI · x.com

    5. 27 days earlier
    6. Sep 151 post

      • 🚨 Some guy just open-sourced a tool that converts pdfs to markdown at 100 pages per second. It's called OpenDataLoader. It runs entirely on CPU and handles complex layouts, tables, and nested…

        Read full on X, posted by @mdancho84

        @mdancho84 · x.com

    7. 1 month earlier
    8. Aug 161 post

      • This might be the docling and marker killer for PDF parsing. OpenDataLoader PDF is an open source parser that converts PDFs into clean Markdown, JSON with bounding boxes, and HTML, built for feeding…

        Read full on X, posted by @oliviscusAI

        @oliviscusAI · x.com

    9. 8 days earlier
    10. Aug 81 post

      • • #1 benchmark accuracy at 0.907 overall and 0.928 for tables • Outputs Markdown, JSON with bounding boxes, and HTML from any PDF • First open-source tool for end-to-end auto-tagging to Tagged PDF

        Read full on X, posted by @the_osps

        @the_osps · x.com

    11. Aug 21 post

      • OpenDataLoader PDF 是一个面向 RAG、知识库和文档处理场景的 PDF 解析工具，支持将任意PDF转换为Markdown/JSON/HTML格式，并提供本地模式和混合AI模式来处理复杂表格、扫描件、公式和图表，同时，它是首个可端到端自动为无标签 PDF 生成无障碍标签（Tagged PDF）的开源工具。

        Read full on X, posted by @weiwei2018831

        @weiwei2018831 · x.com

    12. 2 months earlier
    13. Jun 141 post

      • 强烈推荐所有做 RAG 的人收着这个项目，这款 PDF 解析器比 Marker 快 116 倍，准确率更高，本地 CPU 就能跑还完全开源。 叫做OpenDataLoader PDF， 专为 RAG 管道打造的 PDF 解析器， 基准综合第一，得分 0.907，GitHub 2.4 万星🌟， 搭过 RAG 的朋友应该都懂那种绝望， PDF 进去之后，阅读顺序乱了，表格压成一行，…

        Read full on X, posted by @AYi_AInotes

        @AYi_AInotes · x.com

    14. 11 days earlier
    15. Jun 31 post

      • [3/6] 💻 GitHub Trending NousResearch's hermes-agent GitHub project is trending, billed as an AI agent that improves over time.

        Read full on X, posted by @ProbBrain

        @ProbBrain · x.com

    16. Jun 21 post

      • 别再被PDF转换坑了！表格乱码、排版崩、还得花钱买服务，OpenDataLoader直接免费开源给你兜底👇 1️⃣ CPU就能跑，不用GPU 2️⃣ 不要云端、不要API Key 3️⃣ 全程本地，数据零外传 连机密文件都能放心喂，PDF转Markdown还原表格标题，这波是真香。

        Read full on X, posted by @NFTCPS

        @NFTCPS · x.com

    You might also like

    Repositories close to opendataloader-project/opendataloader-pdf
    FeaturedAdvertise to 180K+ monthly visitors
    Omnigraph

    Versioned graph database on object storage. Git-style workflows and multimodal retrieval

    Busbar

    Control what AI can do before it acts

    Bifrost

    Fastest Enterprise AI Gateway for Routing, Governing, and Securing all your AI Traffic

    Websitebench

    Can AI agents reverse-engineer real websites?

    run-llama/liteparse

    Rust

    A fast, helpful, and open-source document parser

    13k941

    SoMarkAI/OXR

    Python

    An open-source document parsing model with SOTA accuracy and speed, using an RSI loop during post-training.

    3.7k247

    scub-france/docling-Studio

    Python

    Visual document analysis studio powered by Docling — configure the extraction pipeline, inspect text, tables and bounding boxes in the browser, then chunk, embed and index into OpenSearch and Neo4j.

    27129

    NameetP/pdfmux

    Python

    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.

    8614

    mindsdb/aipdf

    Python

    A tool to OCR PDFs using gen-AI models

    597

    docling-project/docling

    Python

    Get your documents ready for gen AI

    70.3k5.5k

    beatrizalmeidaf/papero-pdf-text-extractor

    Python

    Fast, open-source PDF text extraction API. Files never stored.

    2145

    raphaelmansuy/edgeparse

    Rust

    EdgeParse converts any digital PDF into Markdown, JSON (with bounding boxes), HTML, or plain text — deterministically, without a JVM, without a GPU, and with best-in-class accuracy on the 200-document benchmark suite included in this repository.

    15721

    huridocs/pdf-document-layout-analysis

    Python

    A Docker-powered service for PDF document layout analysis. This service provides a powerful and flexible PDF analysis service. The service allows for the segmentation and classification of different parts of PDF pages, identifying the elements such as texts, titles, pictures, tables and so on.

    1.4k152