LangGraph OSS Agents in a TEE

What is this?

This is a LangGraph OSS server running inside a Trusted Execution Environment (TEE). Build and deploy agentic workflows with hardware-level security, cryptographic attestation, and zero dependency on external license servers.

This deployment uses the open-source LangGraph library (MIT-licensed) wrapped in a custom FastAPI server, providing a fully self-hosted solution with no LangSmith or proprietary platform dependencies.

TEEs provide a tamper-proof secure boundary where your agents run. Everything operates within hardware-protected memory that guarantees the following:

• End-to-end privacy: Your data is encrypted all the time, even during compute when it's being processed by the agent. No one, including the host can see your data.
• Tamper-proof execution: TEEs prevent unauthorized access or modification of running code and data without detection.
• Verifiable Workloads: TEEs provide a proof of what code is running inside them, and can attest to the exact version of LangGraph OSS that is being run

Try it now (2 agents deployed)

Test the deployed agents directly from your browser:

curl -X POST https://langgraph-demo.lunal.dev/invoke \
  -H "Content-Type: application/json" \
  -d '{"input": {"messages": ["Hello from LangGraph!"]}}'

curl -X POST https://langgraph-demo.lunal.dev/agents/tool/invoke \
  -H "Content-Type: application/json" \
  -d '{"input": {"messages": [{"role": "user", "content": "What is the square root of 144 plus 10?"}]}}'

Stream example (Server-Sent Events):

curl -X POST https://langgraph-demo.lunal.dev/stream \
  -H "Content-Type: application/json" \
  -d '{"input": {"messages": ["Hello!"]}}'

What is Lunal?

Lunal is the trusted compute company that makes TEEs simple, usable, and scalable. We provide unified software and infrastructure for deploying AI workloads in TEEs with zero configuration.

Learn more about Lunal and why secure AI needs TEEs.