CoreWeave Database brings PostgreSQL inside AI compute clusters
CoreWeave made its managed PostgreSQL service generally available inside CKS clusters alongside GPU workloads.
AT A GLANCE
Key points
- Managed PostgreSQL runs on CPU nodes inside the customer’s CKS cluster.
- The service includes high availability, continuous backups and point-in-time recovery.
- pgvector keeps vector search and application data in the same database.
What is changing?
CoreWeave has made CoreWeave Database generally available. The managed PostgreSQL-compatible service runs on CPU nodes inside a customer’s CoreWeave Kubernetes Service (CKS) cluster, while training and inference applications connect through an in-cluster Kubernetes service. This reduces the need to manage a separate cross-cloud link and egress path.
The service includes high availability with a primary and read replicas, automatic failover, continuous backups, point-in-time recovery, encryption in transit and at rest, and pgvector support. CoreWeave builds the PostgreSQL operation on CloudNativePG and manages patching, monitoring, backups and storage. General availability is a provider announcement; latency, cost and resilience should still be measured with production workloads.
Explore the original sources
Source date: 11 November 2026.
Published by AI Radar: 11 Nov 2026, 18:03 (Istanbul, UTC+3).
FOLLOW THE TOPIC
Topics and tags
Share your discovery.
Send this story to a friend.
Reader comments
What do you think about this development? Share your experience or question. Comments are published after editorial approval.
Your name/nickname and comment become public if approved. Read: Privacy notice.
Loading comments…