Question 1

Is Exa or Tavily better?

Accepted Answer

Tavily scores 86.0 and Exa scores 84.0 on the tashan score, which measures upkeep and freshness gated by real adoption. Neither number is a security audit and neither can be bought. The gap is narrow, so compare the evidence rather than the headline.

Question 2

Are Exa and Tavily safe to install?

Accepted Answer

Exa: no known advisories, no build provenance. Tavily: no known advisories, no build provenance. Every capability tashan measures is checked against the OSV advisory database at the version you would install today, for install-time scripts and for build provenance. The audit reads public evidence and never executes anything.

Question 3

How were these two compared?

Accepted Answer

Both were measured on the same day by the same scorer, from public signal only — npm download volume and publish cadence, repository activity, maintainer count and registry status. Nobody can pay to change a score, a rank or a listing.

	Exa	Tavily	what it means
tashan score	84	86	upkeep + freshness, gated by adoption
Adoption evidence	15k/wk	33k/wk	the raw public signal the score came from
Last release	active	active	npm publish or repo push
Upkeep	99	98	cadence, maintainers, status
Expertise grade	not graded	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	existence of findings is always free; the detail a licence buys is on each dossier
Licence	MIT	MIT
Maintainers	more than one	more than one	bus-factor risk

Exa vs Tavily

Install either