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

Bifrost
Bifrost
It's a plan
It's a plan
OfinTech Desk
OfinTech Desk
Omnigraph
Omnigraph
Busbar
Busbar

google/langextract

A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.

Visit GitHub
Python
39.3k
2.9k
29 contributors
Apache License 2.0
website
AchievementsView all →
FeaturedAdvertise to 180K+ monthly visitors
Bifrost

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

It's a plan

Open-source Linear alternative

An issue tracker where AI agents take the work you assign them

OfinTech Desk

An open-source AI workspace for finance and accounting teams, in which every figure is traced to its source

Omnigraph

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

Busbar

Control what AI can do before it acts

Momentum

How fast google/langextract 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 20 – Nov 19, 2026

Stars +734 in 61 days

050100150
137

Forks +94 in 61 days

0510
7

Merged PRs 29 in 61 days

0123
3

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

Not in the Trendshift top 25 in this period

Sep 20Sep 28Oct 6Oct 14Oct 22Oct 30Nov 7Nov 15
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
Sun, Sep 20, 2026+7+11
Mon, Sep 21, 2026+11+11
Tue, Sep 22, 2026+5+10
Wed, Sep 23, 2026+15+30
Thu, Sep 24, 2026+74+40
Fri, Sep 25, 2026+137+60
Sat, Sep 26, 2026+19+20
Sun, Sep 27, 2026+9+10
Mon, Sep 28, 2026+10+00
Tue, Sep 29, 2026+11+20
Wed, Sep 30, 2026+5+00
Thu, Oct 1, 2026+2+00
Fri, Oct 2, 2026+0+10
Sat, Oct 3, 2026+0+30
Sun, Oct 4, 2026+0+11
Mon, Oct 5, 2026+2+22
Tue, Oct 6, 2026+0+02
Wed, Oct 7, 2026+4+00
Thu, Oct 8, 2026+7+11
Fri, Oct 9, 2026+0+11
Sat, Oct 10, 2026+4+10
Sun, Oct 11, 2026+1+01
Mon, Oct 12, 2026+0+01
Tue, Oct 13, 2026+9+10
Wed, Oct 14, 2026+10+02
Thu, Oct 15, 2026+7+12
Fri, Oct 16, 2026+4+00
Sat, Oct 17, 2026+4+01
Sun, Oct 18, 2026+6+00
Mon, Oct 19, 2026+5+10
Tue, Oct 20, 2026+2+10
Wed, Oct 21, 2026+6+20
Thu, Oct 22, 2026+18+10
Fri, Oct 23, 2026+13+40
Sat, Oct 24, 2026+17+30
Sun, Oct 25, 2026+8+20
Mon, Oct 26, 2026+5+30
Tue, Oct 27, 2026+11+20
Wed, Oct 28, 2026+86+62
Thu, Oct 29, 2026+57+70
Fri, Oct 30, 2026+18+30
Sat, Oct 31, 2026+6+20
Sun, Nov 1, 2026+3+40
Mon, Nov 2, 2026+28+53
Tue, Nov 3, 2026+7+01
Wed, Nov 4, 2026+4+02
Thu, Nov 5, 2026+7+00
Fri, Nov 6, 2026+1+01
Sat, Nov 7, 2026+4+13
Sun, Nov 8, 2026+7+10
Mon, Nov 9, 2026+10+10
Tue, Nov 10, 2026+3+11
Wed, Nov 11, 2026+5+20
Thu, Nov 12, 2026+3+00
Fri, Nov 13, 2026+3+00
Sat, Nov 14, 2026+1+10
Sun, Nov 15, 2026+7+30
Mon, Nov 16, 2026+7+10
Tue, Nov 17, 2026+13+10
Wed, Nov 18, 2026+4+30
Thu, Nov 19, 2026+2+00
Total+734+9429
  • 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

    Dec 22, 2025 – Feb 12, 2026#1 on 2 days

    #1#5#10#15#20#25
    Top 10
    Nov 2025Jan 2026MarMayJulSep
    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 google/langextract, and every badge it has earned
    1. Nov 171 post
      • Your model got the answer right. Then a trailing comma broke json.loads(). Retry wrappers catch bad JSON and re-ask the model. Constrained decoding makes the bad token impossible. Which you need…

        Read full on X, posted by @AsWill11

        @AsWill11 · x.com

    2. 19 days earlier
    3. Oct 291 post
      • 做 AI 产品别只会「再改一版提示词」——这 6 个开源项目,把规格、评测、原型、调研串起来: 1 → Spec Kit(GitHub 官方 · 约 14.4 万星) 先写规格再让 Agent 写代码,Copilot / Claude / Cursor 都能接 2 → Promptfoo(约 2.7 万星) 提示词 / Agent 并排评测 + 红队,发版前有数字可看 3 →…

        Read full on X, posted by @perry_weijie

        @perry_weijie · x.com

    4. 17 days earlier
    5. Oct 121 post
      • 1/4 AI读完一部长篇,输出数字该怎么验? Google开源的LangExtract有《罗密欧与朱丽叶》全文案例:文档示例输出4,088条抽取记录。 其中“153 unique characters”值得检查。下面拆官方代码和文档示例输出,未自行复跑。

        Read full on X, posted by @X50s5me8zP30669

        @X50s5me8zP30669 · x.com

    6. Oct 91 post
      • AI 能输出合法 JSON,不代表抽取正确。 LangExtract 文档提醒:模型可能把示例内容带进结果;找不到原文位置时,char_interval 会是 None。 我的建议:先隔离无出处字段,再核对属性和上下文;有出处也不等于理解正确。

        Read full on X, posted by @qianduankaifa

        @qianduankaifa · x.com

    7. 21 days earlier
    8. Sep 181 post
      • 我刚开始以为Jev就是谷歌的langextract项目的翻版。都是结构化输出,其实完全不一样。

        Read full on X, posted by @reiy_leo

        @reiy_leo · x.com

    9. 1 month earlier
    10. Aug 131 post
      • Google just dropped LangExtract on Hugging Face Spaces An interactive demo for their new library that extracts structured information from unstructured text using LLMs with precise grounding and…

        Read full on X, posted by @HuggingApps

        @HuggingApps · x.com

    11. 22 days earlier
    12. Jul 221 post
      • 🚨 Google's 𝐥𝐚𝐧𝐠𝐞𝐱𝐭𝐫𝐚𝐜𝐭 has crossed 37k stars on GitHub. The core idea: point an LLM at unstructured text and get back structured extractions that are grounded in the source, not…

        Read full on X, posted by @DataScienceDojo

        @DataScienceDojo · x.com

    13. Jul 211 post
      • GOOGLE JUST KILLED THE DOCUMENT EXTRACTION INDUSTRY. it's called langextract. ▸ extracts structured data from unstructured text ▸ maps every entity back to its exact source location ▸ handles 100+…

        Read full on X, posted by @oliviscusAI

        @oliviscusAI · x.com

    14. Jul 182 posts
      • • Maps every extraction to its exact location in the source text • Enforces consistent output schema using few-shot examples and controlled generation • Optimized for long documents with chunking,…

        Read full on X, posted by @the_osps

        @the_osps · x.com

      • Google just killed the document extraction industry. LangExtract: Open-source. Free. Better than $50K enterprise tools. What it does: → Extracts structured data from unstructured text → Maps EVERY…

        Read full on X, posted by @ParamSiddh

        @ParamSiddh · x.com

    You might also like

    Repositories close to google/langextract
    FeaturedAdvertise to 180K+ monthly visitors
    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

    OfinTech Desk

    An open-source AI workspace for finance and accounting teams, in which every figure is traced to its source

    Busbar

    Control what AI can do before it acts

    It's a plan

    Open-source Linear alternative

    An issue tracker where AI agents take the work you assign them

    langchain-ai/langchain-extract

    Rich Text Format

    🦜⛏️ Did you say you like data?

    1.2k125

    eyurtsev/kor

    Python

    LLM(😽)

    1.7k93

    shcherbak-ai/contextgem

    Python

    Extract structured data and insights from documents using LLMs and decision models

    2.1k199

    yifanfeng97/Hyper-Extract

    Python

    Hypergraph is more powerful. Transform unstructured text into structured knowledge with LLMs. Graphs, hypergraphs, and spatio-temporal extractions — with one command.

    4.2k504

    Zipstack/unstract

    Python

    LLM-Driven Extraction of Unstructured Data — Built for API Deployments & ETL Pipeline Workflows

    7.5k790

    deanmalmgren/textract

    HTML

    extract text from any document. no muss. no fuss.

    4.7k701

    numindai/nuextract

    Jupyter Notebook
    27324

    Unstructured-IO/unstructured

    HTML

    Convert documents to structured data effortlessly. Unstructured is open-source ETL solution for transforming complex documents into clean, structured formats for language models. Visit our website to learn more about our enterprise grade Platform product for production grade workflows, partitioning, enrichments, chunking and embedding.

    15.8k1.5k

    enoch3712/ExtractThinker

    Python

    ExtractThinker is a Document Intelligence library for LLMs, offering ORM-style interaction for flexible and powerful document workflows.

    1.6k183