Integrations / LangGraph
Keep your graph. Watch it run.
Sulcus instruments your compiled graph’s normal invoke and stream calls. LangGraph still owns scheduling, nodes, tools, state and checkpoints.
Available nowSulcus adds
A live view of graph execution.
- Graph, chain and node steps from LangGraph callbacks.
- Model calls with reported token usage, where the model uses LangChain callbacks.
- Tool start, completion and failure, where callbacks expose them.
- An optional per-run token limit that blocks the next model call once reached.
- Stop control and a retained history of every run.
LangGraph keeps
The workflow and its state.
- Graph definition, routing, scheduling and tool execution.
- Checkpoint storage and state persistence.
- Interrupts and what your application does with them.
- Error handling and side effects in your code.
How it attaches
Around your normal graph calls.
When a project selects LangGraph, Sulcus activates its instrumentation in the run’s container and wraps the invoke, ainvoke, stream and astream calls on compiled graphs. Your application calls its graph as usual.
OBSERVATION BOUNDARY- Runs the workflow
- LangGraph
- Instrumented calls
- Compiled graph invoke / stream
- Token source
- Framework- and provider-reported usage
- Not captured
- Prompts, model outputs, tool payloads
Boundaries
What this integration doesn’t do.
Sulcus Cloud doesn’t offer approvals for LangGraph interrupts, and it doesn’t move tool calls into another executor or replace the graph’s own checkpoints.
The token limit relies on reported usage. A request already in flight can report an overage when it completes. Sulcus then records it and ends the run.
Get started
Run your first agent in Sulcus.
Point Sulcus at a public Git repository, pick the entrypoint and framework, and watch the run live.
Python · public HTTPS Git repos · LangGraph, CrewAI, OpenAI Agents SDK
