A
loop-engineering
90.1
11,796 stars · MIT
Workflow Automation
puppeteer leads by 9.0 · clear
A
90.1
11,796 stars · MIT
B · leads
99.1
95,849 stars · Apache-2.0
loop-engineering versus puppeteer is a Workflow Automation comparison assembled from public repository metrics, the license on file, and whether each product can be self-hosted. Both projects are written mainly in TypeScript. The composite score is 90.1 for loop-engineering and 99.1 for puppeteer.
puppeteer has 95,849 GitHub stars to loop-engineering's 11,796, a gap of 84,053 (8.13×). Forks are 1,583 for loop-engineering and 9,607 for puppeteer. On the log scale used inside this pair, adoption is 82 versus 100, and the fork community is 80 versus 100.
Push history: loop-engineering was last pushed on 17 November 2026 (0 days ago), and puppeteer was last pushed on 17 November 2026 (0 days ago). Open issues stand at 23 for loop-engineering (0.002 per star) and 201 for puppeteer (0.002 per star). Issue-health scores are 96 and 96; activity scores are 100 and 100.
loop-engineering 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. puppeteer is listed as Apache-2.0, 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. License scores in this pair are 96 for loop-engineering and 96 for puppeteer. This is a procurement signal, not legal advice.
In Workflow Automation, both loop-engineering (11,796 stars) and puppeteer (95,849 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: loop-engineering is open source, puppeteer is open source.
puppeteer is ahead on every scored dimension that is not level. Level dimensions: recent activity, issue health, license flexibility, self-hosting. The widest gap is fork community at 20 points (80 vs 100), and the tightest is self-hosting at 0 points (100 vs 100).
puppeteer finishes ahead at 99.1 against loop-engineering at 90.1, a 9.0 point clear 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 | loop-engineering | puppeteer |
|---|---|---|
| GitHub stars | 11,796 | 95,849 |
| Forks | 1,583 | 9,607 |
| Open issues | 23 | 201 |
| Adoption | 82 | 100 |
| Activity | 100 | 100 |
| Community | 80 | 100 |
| Issue health | 96 | 96 |
| License | 96 | 96 |
| Self-hosting | 100 | 100 |
| Composite | 90.1 | 99.1 |
Practical patterns, starters & CLI tools for loop engineering with AI coding agents. Design systems that prompt and orchestrate agents (inspired by Addy Osmani and Boris Cherny). Includes loop-audit, loop-init, loop-cost.
JavaScript API for Chrome and Firefox
puppeteer has more GitHub stars: 95,849 versus 11,796 for loop-engineering. The gap is 84,053 stars.
Both were last pushed on 17 November 2026.
Yes. This catalog marks both loop-engineering and puppeteer as self-hostable. Confirm each project's deploy docs before you plan a migration.
loop-engineering 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. puppeteer is listed as Apache-2.0, 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.
puppeteer scores 99.1 and loop-engineering scores 90.1. This page calls that a clear lead for puppeteer.