LangGraph

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

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.

The Trust Runtime wraps a LangGraph Agent with the full trust stack: identity attestation, content Guards, tool-permission enforcement, and audit. Install the adapters extra:

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.

Python

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")]})

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) and .attestation (the identity-verification result).

Execution Flow

On invoke, a SecureGraph runs three stages:

1. Guard the input

   Runs the input through Dome’s input Guards.

2. Execute the graph

   Executes the underlying compiled graph.

3. Guard the output

   Runs the graph output through Dome’s output Guards.

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.

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.

Passing Compile Options

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

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

Next Steps

Trust Runtime

Identity, tool permissions, and attestation

LangChain

Content Guards for LangChain chains