Reflex vs Shiplight
These two are level on the tashan score (within 2 points), so the score does not decide it. The evidence rows below are where they differ. 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 ›
| Reflex | Shiplight | what it means | |
|---|---|---|---|
| tashan score | 69 | 71 | upkeep + freshness, gated by adoption |
| Adoption evidence | 1k/wk | 2k/wk | the raw public signal the score came from |
| Last release | active | active | npm publish or repo push |
| Upkeep | 72 | 73 | cadence, maintainers, status |
| Expertise grade | solid | not graded | 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 | — | — | |
| Maintainers | one primary | one primary | bus-factor risk |
Install either
Reflex
claude mcp add reflex -- npx -y reflex-browserShiplight
claude mcp add shiplight -- npx -y @shiplightai/mcpNeither 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: Reflex · Shiplight.