Report card

Do AI agents pick Upstash?

How often agents choose Upstash when a developer needs caching & kv — measured across Claude, GPT, Gemini.

Upstash

#3 of 5 caching
6%Pick Rate
95% CI 3%12%

When developers ask an AI agent for caching, Upstash is picked 6% of the time — ranking #3 of 5 measured across Claude, GPT, Gemini.

Picked 6% Named, not picked 6% Never surfaced 87%

Beaten by Redis (59%), Vercel KV (8%).

Awareness

4.1M package downloads / week

Known but not preferred — widely used, but agents pick competitors. That's a preference problem, not awareness.

0 docs in FineWeb (10BT sample) · 958 URLs in Common Crawl

In the raw web crawl, but thin in the filtered corpus models actually train on — an awareness gap at the source.

AdoptionDid the pick convert to installs? Public Adoption = npm downloads of your packages. The proof half of the funnel.

14.2M installs / month ▲ 14% MoM

Growing despite a low Pick Rate — winning the agent pick is upside, not a dependency.

Get the full report

The per-model and per-surface breakdown for Upstash — where it wins, where it loses, and to whom — plus an alert when the Pick Rate moves.

About Upstash

A serverless Redis service accessible over HTTP/REST.

Upstash provides a hosted Redis database that communicates over HTTP rather than a persistent TCP connection, making it suitable for serverless and edge environments where traditional Redis clients don't work well. Developers use it for caching, rate limiting, and session storage in applications deployed on platforms like Vercel, Cloudflare Workers, or AWS Lambda.

Where to start

Create a database on the Upstash console, then use the REST API credentials to connect via the Upstash Redis client package. No persistent connection setup is required.

Install

Links and summary verified from public sources.

The rest of the Caching & KV ranking

← Full Caching & KV leaderboard · How this is measured