Enterprise Security

Security for CortexDB should be planned the same way you plan security for other stateful application infrastructure: around identity, network boundaries, storage controls, auditing, and operational responsibility.

This page focuses on those deployment considerations at a public, high level.

Authentication and access

Applications typically authenticate to CortexDB using bearer credentials.

curl https://your-cortexdb/v1/recall \
  -H "Authorization: Bearer your-api-key"

For production use, teams should define:

• how application credentials are issued and rotated
• which services and operators are allowed to access CortexDB
• how tenant, workspace, or environment boundaries are enforced in application use

Encryption and transport protection

Self-hosted deployments should follow your organization’s standards for:

• encrypting sensitive data according to policy
• protecting secrets and service credentials
• terminating TLS or applying network-layer encryption
• restricting access to trusted networks and workloads

Tenant governance

Many teams use CortexDB in multi-tenant or multi-workspace environments.

In those cases, security planning should include:

• clear tenant scoping in applications and integrations
• environment separation for development, staging, and production
• least-privilege access for services that read or write memory
• review paths for retention, deletion, and data handling requirements

Auditability

Production deployments should make memory operations observable and reviewable.

That usually means capturing:

• who or what system accessed the service
• what action was performed
• which tenant or workspace was affected
• whether the operation succeeded or failed

See Audit Trail for the broader governance view.

Compliance planning

If you are operating in a regulated environment, CortexDB should be deployed as part of your broader compliance program rather than as a standalone exception.

Typical topics to review include:

• data residency requirements
• retention and deletion policies
• incident response and audit evidence
• vendor and provider controls when external AI services are used

Shared responsibility

Security posture depends on deployment model.

• In managed environments, focus on application identity, access, and usage policy.
• In self-hosted environments, also plan for networking, secrets, storage, monitoring, backups, and operator procedures.

Next Steps