New!v1.3.0 just released

The most performant in-memory data store on Earth.

Dragonfly is a drop-in Redis® replacement that is high-performance, low-complexity, and built for scale. Dragonfly's modern architecture enables it to scale vertically to support millions of requests per second and terabyte-sized workloads, all on a single instance.

Benchmark on AWS r6gn.16xlarge. Snapshot benchmark on AWS c6gn.16xlarge. Source.

Fully compatible with Redis

Dragonfly is a drop-in Redis replacement, meaning it uses the same APIs and is compatible with all of the same SDKs and tooling. Teams that switch from Redis to Dragonfly get huge performance gains and simpler system to operate, all without changing code.

Better performance

With non-contending, multi-threaded processes, Dragonfly is architected to deliver the performance that modern applications require: millions of operations per second, all from a single instance.

Simplified Operations

Dragonfly is architected to scale vertically on a single machine, saving teams the cost and complexity of managing a multi-node cluster. For in-memory datasets up to 1TB, Dragonfly offers the simplest and most reliable scale on the market.

Lower Cost

Dragonfly utilizes unique and innovative algorithms and data structures, including dashtable and denseSet . This makes Dragonfly on average 30% more efficient than Redis, meaning you can achieve the same performance and scale on less hardware, significantly reducing total infrastructure costs. In addition, Dragonfly is much more simple to operate, resulting in a far lower total cost of ownership.

A new in-memory data store, architected for today