Security and governance
Let AI agents safely touch
real business data.
ObjectOS security is not about keeping AI away from business systems. It is about letting agents read, analyze, and move work forward inside explicit identity, permission, tool, approval, and audit boundaries. Data stays on your infrastructure, and every AI step is constrained by the runtime.
- Agent
- inherits user identity
- Tool
- governed access path
- Audit
- approval and evidence
AI agent safety model
AI agent safety model
ObjectOS does not treat the model as an administrator. AI first works through business objects, then uses declarative tools to query, analyze, or trigger actions. Tool input is validated, mutating work goes through approval, and every call is constrained by the same permission system.
- 01
Acts as a user
An agent represents a signed-in user, not an unrestricted service account. If the user cannot see a record, the agent cannot see it either.
- 02
Uses governed tools
Agents call structured query, action, and metadata tools instead of owning a raw database connection or dumping whole tables into prompts.
- 03
Queues changes
Tools that modify metadata or sensitive state enter a pending-action queue so reviewers can inspect the diff before applying it.
- 04
Leaves evidence
Conversations, tool calls, reads, writes, approvals, rejections, and permission changes can be written to audit logs.
Data residency
Data residency
ObjectOS does not require moving business data into our cloud. The runtime connects to your databases, storage, and identity systems, so residency follows your deployment boundary.
| Data | Location | Leaves? |
|---|---|---|
| Business records | Your database | No |
| Users, sessions, OAuth tokens | Your database | No |
| Audit logs | Your database | No |
| Uploaded files | Local disk, S3, or R2 | No |
| Secrets and settings | Your secret manager or encrypted settings store | No |
| AI request context | Your chosen model provider or local model | Only if you configure an external model |
Deployment boundary
Deployment boundary
The default shape is enterprise-network friendly: one Node.js runtime, your database, your secrets, and your ingress. Stricter environments can use file-backed artifacts and offline images.
VPC / private network
Run in your cloud account or private network with only required HTTP/HTTPS and database connectivity.
Local servers
Run with Docker, systemd, or your own platform while connecting local databases, object storage, and identity.
Air-gapped
Use offline container images and a local objectstack.json artifact with no cloud control plane or public internet requirement.
Local models
Point AI services at Ollama, vLLM, or internal model endpoints to keep business context inside your boundary.
Security review FAQ
Security review FAQ
Does ObjectOS phone home?
No. Unless you explicitly configure integrations such as OIDC, email, AI providers, webhooks, or external storage, ObjectOS does not phone home, check a license server, or collect telemetry.
What goes to a model provider?
Only the context required for the model task: conversation context, tool definitions, and necessary tool output. You can use an external model or configure a local model endpoint.
How do we limit agent writes?
Use read-only data sources, object permissions, field permissions, action permissions, and approval queues. Agents cannot bypass runtime permissions or silently apply structural changes.
Who owns TLS, database encryption, and secrets?
Those are deployment responsibilities. ObjectOS provides runtime authorization, audit, API key hashing, and settings encryption; your infrastructure owns TLS, at-rest database encryption, backups, and secret injection.
Is it suitable for regulated environments?
ObjectOS provides the technical primitives: access control, audit, data residency, and isolated deployment. Certification depends on your running deployment, not a binary alone.
Next step
Bring AI close to the business without letting it cross the line.
Confirm how agents identify users, access objects, trigger actions, enter approval, and leave audit evidence before connecting them to real business data.