Real-time data infrastructure that does more.
Redis© compatible, thread-per-core data infrastructure. Better performance, simpler scaling model, all delivered on a smaller infrastructure footprint.
25x
more QPS
than Redis
Throughput
30%
better memory
efficiency
Memory Consumed
Throughput benchmark source
Memory efficiency benchmark source
Trusted By
"By migrating from managed Valkey to Dragonfly Cloud we've been able to cut our cluster size by 70% while also reducing our average and P99 latencies by 50% while further optimizing network cost in ways not possible with ElastiCache Valkey."
Tristan Fletcher, Tech Lead Manager
Instacart
Performance At Scale
Dragonfly is multi-threaded. Redis is not.
Dragonfly’s shared nothing, thread-per-core architecture eliminates the scaling bottlenecks of traditional real-time data infrastructure by utilizing every core on every machine. This means lower latency and higher throughput on a smaller hardware footprint.
Dragonfly
Redis
"We chose Dragonfly as it's architecture allowed us to deliver much better performance-per-dollar across our global footprint than we were able to achieve with AWS ElastiCache."
Harsha Nanjundaiah, Senior Director of Engineering
redBus
Cut Costs
One Dragonfly instance does the work of a Redis cluster.
Dragonfly’s architecture is optimized for modern cloud hardware, eliminating infrastructure waste. This means dramatically lower total infrastructure costs.
1TB cache
Peak throughput of 1M RPS
Standard, 850GB
$6,800 /month
1TB cache
Peak throughput of 1M RPS
$17,082 /month
1TB cache
Peak throughput of 1M RPS
For Redis$19,269 /month
For Valkey$15,415 /month
"We were able to reduce infrastructure costs by 40% by migrating to Dragonfly."
Arya Ketan, Distinguished Engineer
ShareChat
Simplify Operations
Fewer nodes means less complexity.
Dragonfly enables teams to operate with fewer points of failure, less configuration, less operational overhead. This results in a more reliable system that requires much less babysitting.
Dragonfly
Redis
"We were able to cut our cluster size by 80% while also reducing our average and P99 latencies by 40–50%."
Tristan Fletcher, Tech Lead Manager
Instacart