A · leads
browser-use
99.1
121,292 stars · MIT
AI Agents
browser-use leads by 15.9 · decisive
A · leads
99.1
121,292 stars · MIT
B
83.2
80,149 stars · MIT
browser-use versus Prompt-Engineering-Guide is a AI Agents comparison assembled from public repository metrics, the license on file, and whether each product can be self-hosted. browser-use is written mainly in Python; Prompt-Engineering-Guide is written mainly in MDX. The composite score is 99.1 for browser-use and 83.2 for Prompt-Engineering-Guide.
browser-use has 121,292 GitHub stars to Prompt-Engineering-Guide's 80,149, a gap of 41,143 (1.51×). Forks are 13,561 for browser-use and 8,790 for Prompt-Engineering-Guide. On the log scale used inside this pair, adoption is 100 versus 96, and the fork community is 100 versus 95.
Push history: browser-use was last pushed on 17 November 2026 (0 days ago), and Prompt-Engineering-Guide was last pushed on 11 March 2026 (250 days ago). Open issues stand at 596 for browser-use (0.005 per star) and 300 for Prompt-Engineering-Guide (0.004 per star). Issue-health scores are 96 and 96; activity scores are 100 and 36.
Both browser-use and Prompt-Engineering-Guide are listed as MIT. A permissive grant. A company can usually ship it inside a commercial product and keep its own application code private, provided it keeps the copyright notice. The license score is therefore level at 96 versus 96, and the decision moves to adoption, activity, and hosting. This is a procurement signal, not legal advice.
In AI Agents, both browser-use (121,292 stars) and Prompt-Engineering-Guide (80,149 stars) are marked self-hostable. Deploy scores are 100 and 100. Running either one means you own upgrades, backups, and the license duties that follow a modified copy. Pricing labels on file: browser-use is open source, Prompt-Engineering-Guide is open source.
browser-use is ahead on every scored dimension that is not level. Level dimensions: issue health, license flexibility, self-hosting. The widest gap is recent activity at 64 points (100 vs 36), and the tightest is self-hosting at 0 points (100 vs 100).
browser-use finishes ahead at 99.1 against Prompt-Engineering-Guide at 83.2, a 15.9 point decisive margin under the published weights.
Scores are computed inside this pair only. Method and weights.
Bars are scaled within the row. Higher is stronger. Open issues are a raw count, so that row has no bar.
| Signal | browser-use | Prompt-Engineering-Guide |
|---|---|---|
| GitHub stars | 121,292 | 80,149 |
| Forks | 13,561 | 8,790 |
| Open issues | 596 | 300 |
| Adoption | 100 | 96 |
| Activity | 100 | 36 |
| Community | 100 | 95 |
| Issue health | 96 | 96 |
| License | 96 | 96 |
| Self-hosting | 100 | 100 |
| Composite | 99.1 | 83.2 |
Open-source Python library for AI browser agents, plus Browser Use Cloud: stealth browsers and a hosted agent API.
🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.
browser-use has more GitHub stars: 121,292 versus 80,149 for Prompt-Engineering-Guide. The gap is 41,143 stars.
browser-use was pushed more recently: 17 November 2026 versus 11 March 2026 for Prompt-Engineering-Guide. That is 250 days apart.
Yes. This catalog marks both browser-use and Prompt-Engineering-Guide as self-hostable. Confirm each project's deploy docs before you plan a migration.
browser-use is listed as MIT, which this catalog treats as a permissive grant. A company can usually ship it inside a commercial product and keep its own application code private, provided it keeps the copyright notice. Prompt-Engineering-Guide is listed as MIT, which this catalog treats as a permissive grant. A company can usually ship it inside a commercial product and keep its own application code private, provided it keeps the copyright notice. Read both grants before you embed either codebase in a hosted product. This is not legal advice.
browser-use scores 99.1 and Prompt-Engineering-Guide scores 83.2. This page calls that a decisive lead for browser-use.