Run any workload with privacy and verifiability.

SCRT Labs builds SecretAI. SecretVMs use Trusted Execution Environments (TEEs) to protect AI models, agents and sensitive data with hardware-enforced guarantees, even from the infrastructure operator.

A 3D padlock on a circuit board

The challenge

Your infrastructure can’t keep secrets

Traditional cloud leaves AI inference, autonomous agents and sensitive data exposed.

Cloud operators see everything

Standard VMs expose your data and code to cloud providers, hypervisor admins and anyone with privileged access.

Agents need guarantees

Autonomous AI agents handling credentials and sensitive operations need verifiable execution, not just promises.

Compliance demands proof

HIPAA, GDPR and financial regulations require demonstrable data protection, not security theater.

An AI chip on a circuit board

Our solution

Hardware-level privacy for any workload

Workloads run inside secure enclaves protected by CPU- and GPU-level encryption (Intel, AMD, NVIDIA). Not even a root user or the cloud provider can see inside.

  • Memory encryption at the hardware level
  • Cryptographic attestation for verification
  • Protection from insider threats and malware

Products

Confidential infrastructure, your way

From managed AI APIs to fully customizable confidential VMs.

Core product

SecretVMs

Confidential virtual machines powered by TEEs. Run any code, any framework, with cryptographic proof of what is running.

  • Any language, any framework
  • GPU support
  • Remote attestation built in
  • Fully open source
AI

Confidential AI

Pre-configured AI models running inside SecretVMs. Private inference with zero prompt logging.

  • Qwen3.6, Gemma4, GPT-OSS:120B
  • OpenAI-compatible API
  • Custom model deployment
Tooling

Developer Tools

Everything to build, deploy and verify confidential workloads, from CLI to CI/CD.

  • CLI for VMs and authentication
  • GitHub CI/CD integration
  • Verifiable message signing
  • Independent VM verification

Explore SecretAI

How it works

From zero to confidential in minutes

Your existing code just works.

Spin up a SecretVM

Launch a confidential Linux VM inside a hardware TEE from the portal, CLI or API.

Deploy your code

Use the CLI to authenticate and deploy your existing workload. No re-architecture needed.

Verify and trust

Use remote attestation to prove the exact code, firmware and configuration running in a genuine enclave.

Agentic infrastructure

Built for autonomous agents

Agents that can transact, reason and operate, with confidential computing guarantees baked in.

Ready for AI agents

Run autonomous agents in isolated confidential VMs with verifiable integrity, secure key management and built-in MCP server support.

EIP-8004 support

Register agents on-chain, publish their capabilities and let smart contracts interact with them.

Payments via x402

Machine-to-machine micropayments with cryptographic receipts, for confidential AI and VM funding.

Who it’s for

From startups to regulated enterprises

AI & agent builders

Build agents and MCP servers users can actually trust, with private inference and user data isolation.

Healthcare

Process PHI and run diagnostic AI with hardware-enforced privacy.

Financial services

Run trading, fraud and risk models without exposing IP or customer data.

Web3 & infrastructure

Verifiable oracles, confidential smart contracts and trustless bridges.

Run your first confidential workload

Spin up a SecretVM in minutes, or talk to us about your use case.