head to head · open source
page-agent vs ArchiveBox
page-agent has 29,634 GitHub stars, 2,642 forks, 94 open issues and last shipped 2 days ago. ArchiveBox has 28,958 stars, 1,631 forks, 159 open issues and last shipped 3 days ago. page-agent leads on adoption by 2% (29,634 vs 28,958 stars). page-agent is written in TypeScript under MIT; ArchiveBox is written in Python under MIT. page-agent has attracted 9% as many forks as stars, ArchiveBox 6%. page-agent was the more recently maintained of the two, and both are self-hostable with no licence fee.
Two open source projects, one decision. Both are free and self-hostable — the differences are community size, license terms, language stack and release pace.
← all 20902 open source comparisons
Side by side
| page-agent | ArchiveBox | |
|---|---|---|
| GitHub stars | ★ 30K | ★ 29K |
| License | MIT | MIT |
| Written in | TypeScript | Python |
| Last push | 2026-11-04 | 2026-11-03 |
| Forks | ⑂ 2.6K | ⑂ 1.6K |
| Self-hosting | Yes | Yes |
| Data ownership | Your server | Your server |
pick page-agent if
- You weight community size — 30K stars and counting
- You want the MIT license terms
- Your stack matches TypeScript
- You value the larger contributor base for long-term maintenance
pick ArchiveBox if
- You want the ArchiveBox feature set and don't need the biggest community
- You prefer the MIT license terms
- Your stack matches Python
- You evaluated both and ArchiveBox fits your workflow better
About page-agent
Page Agent The GUI Agent Living in Your Webpage. One script gives any web page its own AI agent. 🌐 English 中文 🚀 Demo 📖 Docs 📢 HN Discussion 𝕏 Follow on X ✨ Features 🎯 Easy integration No need for browser extension / python / headless browser . Just in page javascript. Everything happens in your web page. 📖 Text based DOM manipulation No screenshots. No multi modal LLMs or special permissions needed. 🧠 Bring your own LLMs Works with most mainstream models, including locally deployed ones. See supported models. 🐙 Optional chrome extension for multi page tasks. And an MCP Server (Beta) to control it from…
read the full page-agent overview →
About ArchiveBox
ArchiveBox Open source self hosted web archiving. ▶️ Quickstart Demo GitHub Documentation Info & Motivation Community ArchiveBox is a self hosted app that lets you preserve content from websites in a variety of formats. We aim to make your data immediately useful, and kept in formats that other programs can read directly. As output, we save standard HTML, PNG, PDF, TXT, JSON, WARC, SQLite, all guaranteed to be readable for decades to come. ArchiveBox also has a CLI, REST API, and webhooks so you can set up integrations with other services. Without active preservation effort, everything on the internet eventually…
read the full ArchiveBox overview →
More in Data & Analytics
Related comparisons
More Data Extraction & Web Scraping projects
Compare either of these against the rest of the Data Extraction & Web Scraping field.
Frequently asked questions
Is page-agent or ArchiveBox more popular?
page-agent has 29,634 GitHub stars and ArchiveBox has 28,958. page-agent has the larger community by that measure.
Are page-agent and ArchiveBox free?
Both are open source. page-agent is licensed under MIT and ArchiveBox under MIT. Neither carries a licence fee.
What is the difference between page-agent and ArchiveBox?
page-agent is written in TypeScript and ArchiveBox in Python. The practical differences are community size, licence terms, language stack and release cadence — all compared in the table above.
Which should I choose, page-agent or ArchiveBox?
Choose page-agent if you want the larger community (29,634 stars) or its MIT licence terms. Choose ArchiveBox if its feature set, stack or MIT licence fits better. Both are self-hostable.