{"full_name":"getmaxun/maxun","owner":"getmaxun","name":"maxun","shard":"1","url":"https://github.com/getmaxun/maxun","description":"Turn any website into a structured API. Extract, automate, search and monitor the web.","homepage":"https://www.maxun.dev","topics":["automation","no-code","scraper","web-scraper","web-scraping","api","browser-automation","playwright","self-hosted","robotic-process-automation","rpa","agents","data-extraction","webscraping","nocode"],"tag_pages":["agents","api","automation","browser-automation","data-extraction","no-code","nocode","playwright","rpa","scraper","self-hosted","web-scraper","web-scraping","webscraping"],"language":"TypeScript","license":"AGPL-3.0","avatar":"https://avatars.githubusercontent.com/u/139582646?v=4","created_at":"2023-10-23T21:40:19Z","pushed_at":"2026-11-09T09:08:16Z","metrics":{"stars":18464,"forks":1593,"watchers":85,"issues":334,"prs":931,"releases":50,"issues_open":54,"issues_closed":280,"prs_open":39,"prs_closed":37,"prs_merged":855,"discussions":0},"growth":{"day":{"stars":58,"forks":6,"base_day":"2026-11-15"}},"history":{"dates":["2026-11-10","2026-11-11","2026-11-12","2026-11-13","2026-11-14","2026-11-15","2026-11-16"],"stars":[18199,18209,18219,18219,18296,18406,18464],"forks":[1577,1575,1575,1575,1580,1587,1593],"watchers":[null,85,85,85,85,85,85],"issues_open":[null,54,54,54,54,54,54],"prs_open":[null,39,39,39,39,39,39]},"boards":{},"same_owner":[],"issues":[{"number":323,"title":"Register Account not possible","comments":36,"created_at":"2025-01-07T03:06:00Z"},{"number":306,"title":"部署完成访问5173之后可以进入页面，但是在注册页面注册账户时没反应","comments":25,"created_at":"2024-12-31T08:02:24Z"},{"number":534,"title":"Can't create account to get started docker!","comments":15,"created_at":"2025-04-11T00:27:30Z"},{"number":506,"title":"why browser not loading?","comments":9,"created_at":"2025-03-27T16:09:29Z"},{"number":492,"title":"browser.newContext: Target page, context or browser has been closed","comments":9,"created_at":"2025-03-21T02:26:48Z"},{"number":151,"title":"Feature: perform clicks","comments":8,"created_at":"2024-11-07T09:41:34Z"},{"number":758,"title":"docker运行没报错，但是注册不了","comments":5,"created_at":"2025-08-28T05:02:00Z"},{"number":529,"title":"Can someone share the aarch64/arm64 Docker file?","comments":5,"created_at":"2025-04-09T03:39:35Z"}],"discussions":[],"latest_release":{"name":"v0.1.0","tag":"v0.1.0","published_at":"2026-10-25T01:45:20Z","body":"We're moving beyond `0.0.x` and into `0.1.0`!\r\n\r\nThis 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.\r\n\r\nHere's what's new.\r\n\r\n## ⚡ Faster scraping, better results\r\n\r\nScraping is now **4× faster**, dropping from 2.5 seconds to 0.63 seconds in our local benchmark covering text, links, Markdown, HTML, and screenshots.\r\n\r\nWe've also improved the quality of extracted content across 91 real-world pages:\r\n\r\n- **26% higher precision** - less irrelevant content in the output.\r\n- **12% higher F1 score** - a better balance between precision and completeness.\r\n- **20% smaller output** - less data to process downstream.\r\n- **99% recall maintained** - virtually all expected content is still captured, with no page losing recall in our benchmark.\r\n\r\nThe result: faster scraping, cleaner output, and less unnecessary data.\r\n\r\nContent extraction is more precise, output is smaller, and no page lost recall in the benchmark.\r\n\r\n## 🤖 A new AI Mode\r\n\r\nAI Mode has been rebuilt to make natural-language data extraction more useful and reliable.\r\n\r\nPreviously, 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.\r\n\r\nDescribe the data you want and Maxun builds a reusable robot to extract it.\r\n\r\nOnce created, the robot can be run repeatedly without making LLM calls on every run, keeping subsequent extractions fast and cost-efficient.\r\n\r\n**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.\r\n\r\nLearn more here: https://docs.maxun.dev/robot/extract/llm-extraction, https://docs.maxun.dev/robot/agent\r\n\r\n## 🕷️ Crawling is faster and cleaner\r\n\r\nCrawling is now **77% faster**, with our benchmark dropping from 411 seconds to 96 seconds.\r\n\r\nWe've also reduced duplicate and irrelevant data, so crawls return cleaner, more useful results:\r\n\r\n- **100% fewer duplicate links** in the output, down from 28% to zero.\r\n- **50% smaller HTML output per page**, from 280 KB to 139 KB.\r\n- **16% higher Markdown precision**, reducing irrelevant content in extracted pages.\r\n- **No duplicate articles** in the benchmark, down from 23.\r\n\r\nThe result: faster crawls, less redundant data, and cleaner output for downstream processing.\r\n\r\n## 📄 Better document extraction\r\n\r\n\r\nDocument Robots are now better at extracting structured data from large and complex files, including PDFs, spreadsheets, CSVs, and DOCX documents.\r\n\r\n- **More complete results:** Preserve document metadata alongside line items and other records.\r\n- **Better large-file handling:** Recover from truncated model responses and process document chunks in parallel.\r\n- **Improved table parsing:** Preserve table structure, headers, and row order across file formats.\r\n- **More accurate data:** Better handling of dates, international number formats, and duplicate records.\r\n\r\nIn tests with simulated model responses and realistic output limits:\r\n\r\n- **Invoices:** Recovered all 4 header fields and all 60 line items.\r\n- **Bank statements:** Extracted all 300 transactions, up from 25.\r\n- **CSV files:** Extracted all 1,500 orders, up from 5 rows.\r\n\r\nDocument Robots are now substantially more reliable when processing large files and datasets.\r\n\r\n## 🔌 A new MCP server\r\n\r\nThe 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.\r\n\r\nNew one-shot tools include:\r\n\r\n- `maxun_scrape` - Scrape a page as Markdown, HTML, text, links, a summary, or screenshots, with optional Smart Queries.\r\n- `maxun_crawl`- Crawl a website with configurable scope, depth, and include/exclude p","is_prerelease":false},"readme":true,"readme_zh":true,"news":[],"stale":false,"snapshot_at":"2026-11-16T09:23:14Z","history_start":"2026-09-06"}