Puppeteer vs Reflex
Reflex scores 21 points higher on the same evidence, which is a real separation rather than noise. Both are measured the same way, on the same day, from public evidence only — so this is a comparison of two measurements rather than two marketing pages. How we measure ›
| Puppeteer | Reflex | what it means | |
|---|---|---|---|
| tashan score | 48 | 69 | upkeep + freshness, gated by adoption |
| Adoption evidence | 37k/wk | 1k/wk | the raw public signal the score came from |
| Last release | abandoned | active | npm publish or repo push |
| Upkeep | 63 | 73 | cadence, maintainers, status |
| Expertise grade | not graded | solid | an LLM read of its own documentation against a fixed rubric |
| Security audit | no known advisories, no build provenance | no known advisories, no build provenance | a summary — the full audit, free, is on each dossier |
| Licence | MIT | — | |
| Maintainers | more than one | one primary | bus-factor risk |
Install either
Puppeteer
claude mcp add puppeteer -- npx -y @modelcontextprotocol/server-puppeteerReflex
claude mcp add reflex -- npx -y reflex-browserNeither score is a security verdict — "well maintained" and "nothing known is wrong" are different claims, which is why the audit is a separate row and never folded into the number. The full audit for each — the advisory ids, the version that fixes them and anything that runs at install time — is free on its own page: Puppeteer · Reflex.