Self-hosted · Your VPC

Run Enclavia in your VPC

Hardware-enforced egress security for your AI agents. The entire stack runs inside your AWS account — and your agents need no code changes.

Minimum changes to go live

1 · One-time

Provision the stack

Provide your AWS VPC and a few values. One terraform apply provisions the control plane, data plane, and enclave in your account.

Deployment guide →
2 · Per agent

Point agents at the data plane

Python agents: pip install enclavia-agent and set three environment variables. No SDK imports, no core-logic changes.

Agent integration →
3 · Optional

Add your LLM key

For employee chat, add your Anthropic or OpenAI key in the dashboard under Teams → LLM Provider (BYOK). It is encrypted at rest.

The quick version

# 1. Provision (AWS VPC + a few values)
terraform apply

# 2. Integrate an agent — three env vars, zero code changes
pip install enclavia-agent
export ENCLAVIA_API_URL="http://<data-plane>:3001/api/agent/egress"
export ENCLAVIA_API_KEY="<workload-api-key>"
export ENCLAVIA_AGENT_ID="<agent-id>"

What we need from you

  • An AWS account (and permission to create EC2, RDS, and IAM roles).
  • A VPC with subnets to host the stack.
  • A DNS name for your dashboard (e.g. enclavia.acme.com).
  • Your agent workloads (or the repos that run them).

What you get

  • Control plane + data plane + AWS Nitro Enclave, in your VPC.
  • Allowlist & DLP enforcement with NSM attestation on every decision.
  • Audit logs, SOC 2 exports, usage metering, and model routing.
  • Granular RBAC: Super Admin, Org Admin, Auditor.