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

Omnigraph
Omnigraph
Busbar
Busbar
Websitebench
Websitebench
Bifrost
Bifrost

datalab-to/chandra

OCR model that handles complex tables, forms, handwriting with full layout.

#Document parsing
Visit GitHub
Python
12.7k
1.3k
4 contributors
Apache License 2.0
website
AchievementsView all →
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

Websitebench

Can AI agents reverse-engineer real websites?

Bifrost

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

Momentum

How fast datalab-to/chandra 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 17 – Nov 16, 2026

Stars +455 in 61 days

0204060
44

Forks +43 in 61 days

0510
7

Merged PRs 2 in 61 days

012
2

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

Not in the Trendshift top 25 in this period

Sep 17Sep 25Oct 3Oct 11Oct 19Oct 27Nov 4Nov 12
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 PRs
Thu, Sep 17, 2026+5+00
Fri, Sep 18, 2026+8+10
Sat, Sep 19, 2026+12+00
Sun, Sep 20, 2026+9+00
Mon, Sep 21, 2026+4+00
Tue, Sep 22, 2026+5+00
Wed, Sep 23, 2026+3+10
Thu, Sep 24, 2026+9+00
Fri, Sep 25, 2026+2+00
Sat, Sep 26, 2026+4+00
Sun, Sep 27, 2026+3+00
Mon, Sep 28, 2026+3+00
Tue, Sep 29, 2026+10+10
Wed, Sep 30, 2026+2+00
Thu, Oct 1, 2026+11+20
Fri, Oct 2, 2026+26+70
Sat, Oct 3, 2026+13+00
Sun, Oct 4, 2026+20+10
Mon, Oct 5, 2026+3+10
Tue, Oct 6, 2026+4+10
Wed, Oct 7, 2026+3+00
Thu, Oct 8, 2026+44+20
Fri, Oct 9, 2026+10+00
Sat, Oct 10, 2026+3+10
Sun, Oct 11, 2026+1+10
Mon, Oct 12, 2026+3+10
Tue, Oct 13, 2026+6+10
Wed, Oct 14, 2026+2+10
Thu, Oct 15, 2026+4+00
Fri, Oct 16, 2026+3+10
Sat, Oct 17, 2026+5+10
Sun, Oct 18, 2026+2+00
Mon, Oct 19, 2026+2+00
Tue, Oct 20, 2026+4+00
Wed, Oct 21, 2026+7+00
Thu, Oct 22, 2026+19+12
Fri, Oct 23, 2026+14+40
Sat, Oct 24, 2026+10+10
Sun, Oct 25, 2026+14+00
Mon, Oct 26, 2026+6+20
Tue, Oct 27, 2026+21+10
Wed, Oct 28, 2026+18+00
Thu, Oct 29, 2026+12+10
Fri, Oct 30, 2026+5+00
Sat, Oct 31, 2026+9+10
Sun, Nov 1, 2026+6+00
Mon, Nov 2, 2026+10+20
Tue, Nov 3, 2026+7+30
Wed, Nov 4, 2026+7+10
Thu, Nov 5, 2026+5+00
Fri, Nov 6, 2026+4+00
Sat, Nov 7, 2026+2+00
Sun, Nov 8, 2026+1+10
Mon, Nov 9, 2026+0+00
Tue, Nov 10, 2026+2+00
Wed, Nov 11, 2026+3+00
Thu, Nov 12, 2026+10+00
Fri, Nov 13, 2026+8+00
Sat, Nov 14, 2026+5+00
Sun, Nov 15, 2026+0+10
Mon, Nov 16, 2026+2+00
Total+455+432
  • 1#1 on the list
  • 7Rank that day
  • Not trending
4
  • GitHub trending history

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

    Mar 26 – Mar 28, 2026Best #6

    #1#5#10#15#20#25
    Top 10
    Feb 2026AprJunAugOct
    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 datalab-to/chandra, and every badge it has earned
    1. Oct 181 post
      • 😤 扫描 App 一个功能一个会员,识别还按次收费。这 5 个识别全在本地跑:chandra 啃复杂表格和手写体、chineseocr_lite 轻量中文 OCR 连竖排也认、zerox 用视觉模型抽文档、RapidOCR 多语言 ONNX 推理、omniparse 统一转文本。

        Read full on X, posted by @laogeai

        @laogeai · x.com

    2. 1 month earlier
    3. Sep 181 post
      • 🚨Este OCR LEE LA LETRA DE LOS MÉDICOS! Y también: - tablas complejas - ecuaciones matemáticas Se llama Chandra, de Datalab. Y es uno de los OCR más completos que he visto. Puede procesar: 📌 Texto…

        Read full on X, posted by @josesilesdata

        @josesilesdata · x.com

    4. 1 month earlier
    5. Aug 111 post
      • • Tops the external olmocr benchmark • Supports 90+ languages with strong handwriting and form reconstruction • Converts documents to markdown, html, or json with detailed layout

        Read full on X, posted by @the_osps

        @the_osps · x.com

    6. 12 days earlier
    7. Jul 301 post
      • everyone's sleeping on this new ocr model. it's called chandra, from datalab. it just topped independent benchmarks and beat the previous best, dots-ocr. > handles text, tables, and formulas…

        Read full on X, posted by @oliviscusAI

        @oliviscusAI · x.com

    8. 9 days earlier
    9. Jul 211 post
      • Marker is powered by the new Surya OCR 2 model ( which is the highest-scoring model under 1B params on olmocr. Read more at .

        Read full on X, posted by @VikParuchuri

        @VikParuchuri · x.com

    10. Jul 191 post
      • 🚨 Este OCR GRATUITO puede leer letra de médicos, tablas complejas y ecuaciones matemáticas. Se llama **Chandra**, de Datalab. Y es uno de los OCR más completos que he visto. Puede procesar: 📌…

        Read full on X, posted by @josesilesdata

        @josesilesdata · x.com

    11. 23 days earlier
    12. Jun 261 post
      • Going forward, we'll include reproduction scripts with our models when we measure against public benchmarks. I will do the same for Surya OCR 2 (the other potentially affected model) soon.

        Read full on X, posted by @VikParuchuri

        @VikParuchuri · x.com

    13. 23 days earlier
    14. Jun 31 post
      • Someone sent me this unreadable soap label last year. I just tried it with our new model - now you, too, can read the ramblings of Dr. Bronner.

        Read full on X, posted by @VikParuchuri

        @VikParuchuri · x.com

    15. 13 days earlier
    16. May 211 post
      • OCR breaks where documents get messy. This repo targets the messy parts. Chandra OCR 2 is an OCR model for document intelligence that converts images and PDFs into structured HTML, Markdown, or JSON…

        Read full on X, posted by @DanKornas

        @DanKornas · x.com

    17. May 161 post
      • Converts PDFs and images to structured HTML and Markdown preserving layout #CyberSecurity #InfoSec #e0xsecops #TechLeadershi

        Read full on X, posted by @hemran_7282

        @hemran_7282 · x.com

    You might also like

    Repositories close to datalab-to/chandra
    FeaturedAdvertise to 180K+ monthly visitors
    Websitebench

    Can AI agents reverse-engineer real websites?

    Bifrost

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

    Busbar

    Control what AI can do before it acts

    Omnigraph

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

    patsnap/Hiro-Smart-Doc

    Python

    Smart Document API turns PDFs, Office documents, and images into structured layouts, OCR text, tables, formulas, and Markdown for AI-powered document understanding.

    262

    fufankeji/DeepSeek-OCR-Web

    TypeScript

    Out-of-the-box DeepSeek OCR document parsing Web Studio

    57098

    patsnap/Hiro-MOSS-OCR

    Python

    0.3B OCR model which emits structured markup ---- math as latex, table as html, text as markdown.

    746

    zai-org/GLM-OCR

    Python

    GLM-OCR: Accurate × Fast × Comprehensive

    7.6k706

    lightonai/LightOnOCR

    Python

    Turn document pixels into structured, grounded content with LightOnOCR-3

    766

    chatdoc-com/OCRFlux

    Python

    OCRFlux is a lightweight yet powerful multimodal toolkit that significantly advances PDF-to-Markdown conversion, excelling in complex layout handling, complicated table parsing and cross-page content merging.

    2.5k161

    AIAnytime/SmolDocling-OCR-App

    Python

    SmolDocling OCR App built using SmolDocling 256M Model and Streamlit.

    26244

    NanoNets/docstrange

    Python

    Extract and convert data from any document, images, pdfs, word doc, ppt or URL into multiple formats (Markdown, JSON, CSV, HTML) with intelligent structured data extraction and advanced OCR.

    1.6k146

    AdemBoukhris457/Doctra

    Jupyter Notebook

    📄🔍 Parse, extract, and analyze documents with ease 📄🔍

    21433