> ## Documentation Index
> Fetch the complete documentation index at: https://vijil-mintlify-a91c9b66.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# LangGraph

> Secure a LangGraph agent with the Dome Trust Runtime in one call.

<Tip>
  **TL;DR:** Pass your `StateGraph` to `secure_agent()`. It returns a `SecureGraph` that replaces `graph.compile()`, running content Guards on every model call and enforcing tool permissions before each tool executes.
</Tip>

The [Trust Runtime](/concepts/defense/trust-runtime) wraps a LangGraph [Agent](/owner-guide/register-agents/what-is-an-agent) with the full trust stack: identity attestation, content [Guards](/concepts/defense/guard), tool-permission enforcement, and audit. Install the adapters extra:

```bash theme={null}
pip install "vijil-dome[trust,trust-adapters]"
```

## Securing a Graph

Call `secure_agent()` with your uncompiled `StateGraph`. It detects LangGraph automatically and returns a `SecureGraph` that stands in for the compiled graph.

<CodeGroup>
  ```python title="Python" icon="python" theme={null}
  from langgraph.graph import StateGraph
  from vijil_dome import secure_agent

  graph = StateGraph(MyState)
  # ... add nodes and edges ...

  app = secure_agent(
      graph,
      agent_id="travel-agent",
      mode="enforce",
  )

  result = app.invoke({"messages": [("user", "Find me flights from SF to Tokyo")]})
  ```
</CodeGroup>

`secure_agent()` compiles the graph for you and best-effort wraps any tools it finds with permission checks. The returned `SecureGraph` supports the standard execution methods: `invoke`, `ainvoke`, `stream`, and `astream`. It also exposes `.runtime` (the underlying [`TrustRuntime`](/concepts/defense/trust-runtime)) and `.attestation` (the identity-verification result).

## Execution Flow

On `invoke`, a `SecureGraph` runs three stages:

<Steps>
  <Step title="Guard the input">
    Runs the input through Dome's input Guards.
  </Step>

  <Step title="Execute the graph">
    Executes the underlying compiled graph.
  </Step>

  <Step title="Guard the output">
    Runs the graph output through Dome's output Guards.
  </Step>
</Steps>

In `enforce` mode, flagged input or output returns a guarded response of the form `{"messages": [guarded_response]}` instead of the model result. In `warn` mode, violations are logged and execution continues.

<Note>
  Streaming (`stream` / `astream`) applies the output Guard on a best-effort basis after the stream completes, because streamed chunks cannot be retracted once emitted. For strict output enforcement, use `invoke` / `ainvoke`.
</Note>

## Passing Compile Options

Extra keyword arguments flow through to `graph.compile()`:

```python theme={null}
app = secure_agent(
    graph,
    agent_id="travel-agent",
    mode="enforce",
    checkpointer=my_checkpointer,
)
```

## Next Steps

<CardGroup cols={2}>
  <Card title="Trust Runtime" icon="fingerprint" href="/concepts/defense/trust-runtime">
    Identity, tool permissions, and attestation
  </Card>

  <Card title="LangChain" icon="link" href="/developer-guide/protect/integrations/langchain">
    Content Guards for LangChain chains
  </Card>
</CardGroup>