head to head · open source
page-agent vs skills
page-agent has 29,619 GitHub stars, 2,643 forks, 94 open issues and last shipped yesterday. skills has 6,310 stars, 339 forks, 7 open issues and last shipped 2 months ago. page-agent leads on adoption by 369% (29,619 vs 6,310 stars). page-agent is written in TypeScript under MIT; skills is written in Python under MIT. page-agent has attracted 9% as many forks as stars, skills 5%. page-agent was the more recently maintained of the two, and both are self-hostable with no licence fee. The two share 1 topic tag (ai-agents), so they are genuine substitutes rather than adjacent tools.
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 | skills | |
|---|---|---|
| GitHub stars | ★ 30K | ★ 6.3K |
| License | MIT | MIT |
| Written in | TypeScript | Python |
| Last push | 2026-11-02 | 2026-08-24 |
| Forks | ⑂ 2.6K | ⑂ 339 |
| 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 skills if
- You want the skills feature set and don't need the biggest community
- You prefer the MIT license terms
- Your stack matches Python
- You evaluated both and skills 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 skills
What can BrowserAct be used for? BrowserAct enables AI agents and teams to perform real browser automation, web data extraction, and account based workflows. It helps agents get past anti bot walls, hand off to humans across platforms when stuck, run parallel tasks without cross contamination, and isolate multiple accounts in independent browsers, backed by stealth fingerprints, TLS rotation, residential proxies, CAPTCHA solving, and stable fingerprint proxy setups for authenticated sessions. Two usage modes are available: fully cloud managed execution, or local browser control driven by your own agent workflow…
read the full skills 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 skills more popular?
page-agent has 29,619 GitHub stars and skills has 6,310. page-agent has the larger community by that measure.
Are page-agent and skills free?
Both are open source. page-agent is licensed under MIT and skills under MIT. Neither carries a licence fee.
What is the difference between page-agent and skills?
page-agent is written in TypeScript and skills 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 skills?
Choose page-agent if you want the larger community (29,619 stars) or its MIT licence terms. Choose skills if its feature set, stack or MIT licence fits better. Both are self-hostable.