Open-source memory for AI agents that stays correct as facts change
Stage
Not given
Not given
Founded
Not given
Not given
Based in
US
SE
Pricing model
Paid
Freemium
Pricing
Usage-based pay-as-you-go pricing with hourly compute charges; committed contracts available for volume discounts. Hosted option with Anyscale-managed infrastructure or Bring Your Own Cloud deployment available.
Open Source: free self-hosted. Oort Pro: $19/month (VAT included where applicable) with 5,000 saves a month, 25,000 recalls a month, and 1 GB of memory storage.
Key features
Multimodal data curation at scale
Distributed model training with elastic scaling
Batch embedding generation at scale
Multi-cloud deployment and orchestration
Cluster-backed development environments
Workload-specific observability and debugging
Production-grade managed Ray clusters
Access control and governance
GPU budget controls and cost attribution
Post-training with SkyRL and veRL support
Memory recall with millisecond latency and explanations
Automatic fact lifecycle management
Data privacy with secrets scrubbed before saving
Export and forget capabilities
CLI and npm package
Integration with ChatGPT and Claude.ai
Flat-rate pricing that does not scale with history
What makes it different
Built by creators of Ray, the world's most widely adopted AI compute engine
Multi-cloud deployment without code changes
Feels local but runs distributed
Unified GPU pooling across clouds and regions
Facts stay correct as they change, with closed-out old versions
Costs remain flat as memory history grows
Every recall can explain why it returned that memory
Self-hosted with no required API keys for open source