登录

maxun

getmaxunAGPL-3.0活跃维护

把任意网站变成结构化 API，无需写代码就能抓取、自动化、搜索和监控网页数据，适合做数据采集和 RPA 场景。

Turn any website into a structured API. Extract, automate, search and monitor the web.

v0.1.0发布于 2026-10-25 01:45 UTC18,199star +34 / 7 天1,577fork同步于 2026-11-10 11:24 UTC
网页抓取无代码浏览器自动化数据提取RPA
对比 GitHub 官网agentsapiautomationbrowser-automationcrawler

怎么上手

由 README 提炼，执行前请确认
原文 
docker compose up（详见 https://docs.maxun.dev/installation/docker）
硬件要求按 README 说明

README 未说明

有 Docker 镜像
下载：源码 zip·GitHub Releases（安装包）本站不镜像安装包

项目说明

由 README 自动翻译提炼
没人工点评？写下你的经验

开源网页数据平台，把任意网站变成结构化 API，支持抓取、爬取、搜索与监控

把任意网站变成结构化 API，无需写代码就能抓取、自动化、搜索和监控网页数据，适合做数据采集和 RPA 场景。

核心能力

  • 录制浏览器操作生成可复用的提取机器人
  • 用自然语言描述需求由 AI 完成数据提取
  • 将整页转为 Markdown、HTML 并截图
  • 整站爬取并跨页面提取内容
  • 持续监控网页变化并在变动时通知

容易踩的坑

README 未给出具体命令，需按官方文档的 Docker Compose 或本地安装步骤操作；自托管需自行配置环境变量，参见 environment_variables 文档；项目采用 AGPLv3，商业使用需注意许可证义务

内容由模型根据 README 生成，可能不完整或不准确，以官方文档为准。看原文 README

最近发版

5 个版本v0.1.0
全部 release
  1. v0.1.0最新正式版2026-10-25 · 2026-10-25 01:45 UTC

    We're moving beyond 0.0.x and into 0.1.0!

    This release brings major improvements across scraping, crawling, AI-powered data extraction, document processing, and MCP. We've also rebuilt parts of the experience to make Maxun more capable, reliable, and useful as an open-source web data platform.

    Here's what's new.

    ⚡ Faster scraping, better results

    Scraping is now 4× faster, dropping from 2.5 seconds to 0.63 seconds in our local benchmark covering text, links, Markdown, HTML, and screenshots.

    We've also improved the quality of extracted content across 91 real-world pages:

    • 26% higher precision - less irrelevant content in the output.
    • 12% higher F1 score - a better balance between precision and completeness.
    • 20% smaller output - less data to process downstream.
    • 99% recall maintained - virtually all expected content is still captured, with no page losing recall in our benchmark.

    The result: faster scraping, cleaner output, and less unnecessary data.

    Content extraction is more precise, output is smaller, and no page lost recall in the benchmark.

    🤖 A new AI Mode

    AI Mode has been rebuilt to make natural-language data extraction more useful and reliable.

    Previously, AI Mode relied on captured lists (based on recorder mode) from the page. It now builds an extraction robot based on your prompt and the data available on the specified page.

    Describe the data you want and Maxun builds a reusable robot to extract it.

    Once created, the robot can be run repeatedly without making LLM calls on every run, keeping subsequent extractions fast and cost-efficient.

    Want more autonomy? Maxun Cloud also offers Agent, which can discover relevant pages and configure websites to find the data you need. We'll continue improving both AI-powered workflows in upcoming releases.

    Learn more here: https://docs.maxun.dev/robot/extract/llm-extraction, https://docs.maxun.dev/robot/agent

    🕷️ Crawling is faster and cleaner

    Crawling is now 77% faster, with our benchmark dropping from 411 seconds to 96 seconds.

    We've also reduced duplicate and irrelevant data, so crawls return cleaner, more useful results:

    • 100% fewer duplicate links in the output, down from 28% to zero.
    • 50% smaller HTML output per page, from 280 KB to 139 KB.
    • 16% higher Markdown precision, reducing irrelevant content in extracted pages.
    • No duplicate articles in the benchmark, down from 23.

    The result: faster crawls, less redundant data, and cleaner output for downstream processing.

    📄 Better document extraction

    Document Robots are now better at extracting structured data from large and complex files, including PDFs, spreadsheets, CSVs, and DOCX documents.

    • More complete results: Preserve document metadata alongside line items and other records.
    • Better large-file handling: Recover from truncated model responses and process document chunks in parallel.
    • Improved table parsing: Preserve table structure, headers, and row order across file formats.
    • More accurate data: Better handling of dates, international number formats, and duplicate records.

    In tests with simulated model responses and realistic output limits:

    • Invoices: Recovered all 4 header fields and all 60 line items.
    • Bank statements: Extracted all 300 transactions, up from 25.
    • CSV files: Extracted all 1,500 orders, up from 5 rows.

    Document Robots are now substantially more reliable when processing large files and datasets.

    🔌 A new MCP server

    The previous MCP implementation has been replaced with a new, more capable server that exposes Maxun's core functionality directly to AI assistants and MCP clients.

    New one-shot tools include:

    • maxun_scrape - Scrape a page as Markdown, HTML, text, links, a summary, or screenshots, with optional Smart Queries.
    • maxun_crawl- Crawl a website with configurable scope, depth, and include/exclu
  2. v0.0.482026-10-01 · 2026-10-01 17:37 UTC
    查看更新说明

    New Maxun SDKs: Node.js and Python

    Both official SDKs have been rebuilt to make Maxun simpler to use from code. The Node.js SDK (maxun-sdk) and the Python SDK (maxun) now share the same design, so the same few lines work in either language.

    npm install [email protected]
pip install maxun==0.0.13

    ⚠️ Please upgrade to the latest SDK & Maxun App versions for the best experience.

    Everything starts from one object

    Create a robot with one call: the robot name, then a URL, search query or file, then any options. The name is required, and it is how the robot appears in the Maxun dashboard.

    Node.js

    import { Maxun } from 'maxun-sdk';
 
const maxun = new Maxun({ apiKey: 'your-api-key' });
const robot = await maxun.scrape('Maxun', 'https://maxun.dev', { formats: ['markdown'] });
const result = await robot.run();
console.log(result.markdown);

    Python

    from maxun import Maxun
 
async with Maxun(api_key="your-api-key") as maxun:
    robot = await maxun.scrape("Maxun", "https://maxun.dev'", formats=["markdown"])
    result = await robot.run()
    print(result.markdown)

    Every robot type in Maxun is available the same way:

    • maxun.scrape(...): turn a page into Markdown, HTML, text, links, a summary or screenshots
    • maxun.extract(...): extract data with a plain-English prompt, or with selectors
    • maxun.crawl(...): collect content from a whole website
    • maxun.search(...): search the web, and optionally scrape the results
    • maxun.documents.extract(...) / .parse(...): read PDF, DOCX, XLSX, CSV, JPG and PNG files
    • maxun.robots: list, find and delete any robot on your account

    Learn more

    What's Changed

    New Contributors

    Full Changelog: https://github.com/getmaxun/maxun/compare/v0.0.47...v0.0.48

  3. v0.0.47v0.0.47 | Website Monitoring 🔥 2026-09-16 · 2026-09-16 22:04 UTC
    查看更新说明

    🔍 Monitoring

    Maxun can now monitor websites in just a few clicks! Track a website over time and get notified when it changes. You can monitor an entire website, or just a specific part of it. It works with Extract, Scrape, and Crawl robots, and is available through the no-code dashboard, the SDK, the CLI, and the API.

    Note: Monitoring is opt-in and must be explicitly enabled - existing robots are unaffected.

    Learn more here: https://docs.maxun.dev/monitoring

    🖼️ JPG & PNG support for document extraction & parsing

    Document extract and parse now accept JPG and PNG images as input, in addition to existing supported formats.

    What's Changed

    New Contributors

    Full Changelog: https://github.com/getmaxun/maxun/compare/v0.0.46...v0.0.47

  4. v0.0.462026-08-25 · 2026-08-25 08:37 UTC
    查看更新说明

    DOCX Support

    Document parsing and extraction now supports DOCX files.

    Supported document formats are now: PDF, CSV, XLSX, and DOCX.

    Hebrew Language

    Maxun can now be used in Hebrew, making it more accessible to Hebrew-speaking users.

    What's Changed

    New Contributors

    Full Changelog: https://github.com/getmaxun/maxun/compare/v0.0.45...v0.0.46

  5. v0.0.45v0.0.45 2026-08-03 · 2026-08-03 17:28 UTC
    查看更新说明

    📊 CSV & XLSX Support for Document Parsing

    Document Parse and Document Extract now support CSV and XLSX files in addition to PDFs. You can upload spreadsheets directly without needing to convert them to PDFs first.

    ✨ Document Summaries

    Generate AI-powered summaries for PDF, CSV, and XLSX documents, making it easier to quickly understand the contents of large files before extracting structured data.

    Learn more: https://docs.maxun.dev/robot/document

    What's Changed

    New Contributors

    Full Changelog: https://github.com/getmaxun/maxun/compare/v0.0.44...v0.0.45

用户点评

登录用户的真实使用记录，可按版本和硬件筛选
共 0 条

    还没有人点评。第一个说出真实体验的人最有价值。

    README 原文

    未翻译
    在 GitHub 打开

    Sponsors

    What Maxun Does

    • Extract – Extract structured data from any website by emulating real user behavior.
      • Recorder Mode – Record browser actions and turn them into reusable extraction robots.
      • AI Mode – Describe what you need in natural language and extract it with AI.
    • Scrape – Convert full webpages into Markdown, HTML and capture screenshots.
    • Crawl – Crawl entire websites and extract content across pages.
    • Agent – Extract data from websites with AI that autonomously discovers where the data lives.
    • Search – Search the web and extract results with time-based filters.
    • Monitoring – Track websites over time, detect changes, and get notified when they occur.
    • Document Extraction & Parsing – Extract and parse structured data from documents.

    How To Use Maxun

    • Dashboard – Build, run, and manage robots through Maxun's visual interface.
    • API – Integrate Maxun's scraping and extraction capabilities into your applications.
    • SDK – Use Maxun programmatically for scraping, extraction, automation and more.
    • CLI – Create robots, trigger runs, and retrieve data from your terminal.
    • MCP – Connect Maxun to AI agents through the Model Context Protocol.

    Quick Start

    Getting Started

    The simplest & fastest way to get started is to use the hosted version: https://app.maxun.dev.

    Installation

    Maxun can run locally with or without Docker

    1. Setup with Docker Compose
    2. Setup without Docker
    3. Environment Variables
    4. SDK

    Upgrading & Self Hosting

    1. Self Host Maxun With Docker
    2. Upgrade Maxun With Docker Compose Setup
    3. Upgrade Maxun Without Docker Compose Setup

    License

    Project Values

    We believe in fair and responsible use of open source. If you rely on this project commercially, please consider contributing back or supporting its development.

    Support Us

    Star the repository, contribute to the codebase, or sponsor us.

    Contributors

    Thank you to the combined efforts of everyone who contributes!

    相关项目

    同分类里 star 最高的项目
    对比全部 →
    browser-use
    browser-use·Python

    开源的 Python 库，让大模型直接操控浏览器完成点击、填表、抓取等网页任务，省去手写 Playwright 脚本的麻烦。

    浏览器自动化+4电脑 / 浏览器 Agent
    120518+28813k0.13.142026-11-10 09:29 UTC
    browser
    lightpanda-io·Zig

    用 Zig 从零编写的无头浏览器，专为 AI 和自动化场景设计，兼容 CDP 协议，可替代 Playwright、Puppeteer 驱动网页抓取与 Agent 任务。

    无头浏览器+4电脑 / 浏览器 Agent
    41756+2362.1k1.0.32026-11-10 11:18 UTC
    UI-TARS-desktop
    bytedance·TypeScript

    字节开源的多模态 AI Agent 桌面栈，把前沿模型和 Agent 基础设施连起来，让 Agent 能像人一样操作 GUI、浏览器和电脑完成任务。

    多模态Agent+4电脑 / 浏览器 Agent
    39586+214.0kv0.3.12026-10-09 01:29 UTC
    Jobs_Applier_AI_Agent
    feder-cr·Python

    自动投递简历的求职机器人，能按简历匹配度筛选岗位并批量提交申请，睡觉时也能持续找工作。

    求职自动化+4电脑 / 浏览器 Agent
    32444+454.8kusage-counter2026-11-10 02:38 UTC