Teams, SSO and roles
Separate tenants, scoped keys and roles for the people who run it.
Each team's data is isolated at the query layer and gets its own memory store. Members sign in with email or Google, hold roles that control what they can change, and manage API keys that can be created, rotated and revoked.
Workspace · your team
Members
- Anaowner
- Rajadmin
- Samviewer
API keys
- hx_…a1f3active
- hx_…7c20rotated
- hx_…e914revoked
Multi-tenant from the first line
Every row Humane stores is scoped to a tenant, and cross-tenant reads are blocked in the query layer. Memory lives in a separate store per tenant, so isolation holds at the storage level too.
- API keys stored as SHA-256 hashes and shown once
- Create, rotate and revoke keys at any time
- SDK keys only work on SDK routes, so a leaked key can't create keys or invite admins
- A verified email is required before creating keys
Audit log
- 10:42user_42HOLDinaction_guard · reply below minimum length
- 10:40user_17FLAGoverclaim · “you will definitely”
- 10:31user_88BLOCKvalues_boundary · self_harm_encouragement
- 10:05adminEVENTapi_key.revoked by owner
Personal data redacted on export for non-admin roles
Who can do what
- Owner and admin roles required to change engines and onboarding
- Viewer access for people who only need to look
- Google sign-in for your team
- Personal data redacted in audit exports for non-admin roles
- Login throttling per IP and per account
- Rate limits per API key
Access questions
Something else? Ask us.
Works well with
Audit trail
Humane records gate outcomes, safety flags, webhook deliveries, engine decisions and admin actions, each with its reason. When someone asks why the AI did something, you can show them.
ExploreWebhooks and events
Humane posts events to your endpoints as things happen: safety flags, holds and blocks, proactive triggers, takeovers, anomalies and more. Every delivery is signed with HMAC-SHA256, retried on failure and parked in a dead-letter queue if it keeps failing.
ExploreDurable memory
Every turn is stored in a per-tenant vector memory, searchable by meaning. Seed it from your other systems, search it from your own code and erase it when a user asks to be forgotten.
ExploreEvery AI should know who it's talking to.
The safety and human-oversight layer for emotional AI: user state across sessions, risk alerts, safety gates and human takeover, with every decision explained.
