Compliance posture
Need a report, DPA, or BAA? Contact support@supermemory.com or your enterprise contact.
Security controls
Encryption
- In transit: TLS for API and console traffic
- At rest: Industry-standard encryption for stored data (AES-256 class controls in the managed cloud)
Isolation and access
- Container tags enforce hard boundaries between users, tenants, or projects — the primary multi-tenancy primitive.
- API keys authenticate every request. Prefer scoped keys when a client or session must only touch one container.
- Organizations in the console manage members, keys, and billing separation.
Data use
Supermemory is infrastructure for your agents. Paid production usage is not treated as free training corpus for unrelated public models. For contractual wording (DPA, subprocessors, training policies), request the latest legal pack from support.Data residency and deployment options
- Managed cloud — default multi-tenant SaaS.
- Self-hosted binary — full engine on your machine or VPC; embeddings and storage stay where you run it. See Self-hosting.
- Enterprise / dedicated — for stricter residency, air-gap, or custom deployment requirements. See Local vs Enterprise.
Privacy operations you should design for
Deleting a user (right to erasure)
The practical GDPR-style path for app builders:- Scope each end-user (or tenant) to a container tag.
- When the user requests deletion, delete that container’s content via the API / console workflows for documents and memories under that tag.
- Revoke any scoped keys issued for that user.
Connectors and third-party sources
OAuth connectors (Drive, Notion, Gmail, and others) pull content your users authorize. Disconnecting a connector stops future sync; you still control whether already-ingested documents remain in the memory store. Treat connector scope and retention as part of your product privacy policy.Self-host when cloud is not enough
If policy requires data never leave your network, run the self-hosted engine. You bring the model endpoint (including fully offline OpenAI-compatible local models). Enterprise adds managed on-prem / dedicated options with organizational controls.Reliability and support
- Status and incidents are communicated through Supermemory’s status and support channels.
- Support depth scales with plan (community → email → priority → dedicated enterprise).
- Latency targets for retrieval are in the ~sub-300ms p50 range on the managed platform for typical search workloads; always validate on your traffic shape.
Related
Billing & plans
Which tiers include BAAs, seats, and self-host options.
Container tags
How isolation works in the data model.
Authentication
API keys and access for the Developer Platform.
Self-hosting
Keep memory on your infrastructure.