LangGraph Plugin Samples

These samples demonstrate the Temporal LangGraph plugin, which runs LangGraph workflows as durable Temporal workflows. Each LangGraph graph node (Graph API) or @task (Functional API) executes directly inside a workflow or as a Temporal activity with automatic retries, timeouts, and crash recovery.

Samples are organized by API style:

• Graph API (graph_api/) -- Define workflows as StateGraph with nodes and edges.
• Functional API (functional_api/) -- Define workflows with @task and @entrypoint decorators for an imperative programming style.

Samples

Sample	Graph API	Functional API	Description
Hello World	graph_api/hello_world	functional_api/hello_world	Minimal sample -- single node/task that processes a query string. Start here.
Human-in-the-loop	graph_api/human_in_the_loop	functional_api/human_in_the_loop	Chatbot that uses interrupt() to pause for human approval, Temporal signals to receive feedback, and queries to expose the pending draft.
Continue-as-new	graph_api/continue_as_new	functional_api/continue_as_new	Multi-stage data pipeline that uses continue-as-new with task result caching so previously-completed stages are not re-executed.
ReAct Agent	graph_api/react_agent	functional_api/react_agent	Tool-calling agent loop. Graph API uses conditional edges; Functional API uses a while loop.
Control Flow	--	functional_api/control_flow	Demonstrates parallel task execution, for loops, and if/else branching -- patterns that are natural in the Functional API.
Streaming	graph_api/streaming	--	Streams live output from a running workflow via Workflow Streams: node tokens via get_stream_writer() + streaming_topic, plus workflow-side astream progress published with WorkflowStream.topic().publish().
LangSmith Tracing	graph_api/langsmith_tracing	functional_api/langsmith_tracing	Combines LangGraphPlugin with Temporal's LangSmithPlugin for durable execution + full observability of LLM calls. Requires API keys.

Prerequisites

1. Install dependencies:

   uv sync --group langgraph

   This installs the standalone temporalio-langgraph and temporalio-langsmith packages, which require Temporal 1.34.0 or later.

2. Start a local dev server with the Temporal CLI:

   temporal server start-dev

Running a Sample

Most samples have two scripts -- start the Worker first, then the Workflow starter in a separate terminal.

# Terminal 1: start the Worker
uv run langgraph_plugin/<api>/<sample>/run_worker.py

# Terminal 2: start the Workflow
uv run langgraph_plugin/<api>/<sample>/run_workflow.py

For example, to run the Graph API human-in-the-loop chatbot:

# Terminal 1
uv run langgraph_plugin/graph_api/human_in_the_loop/run_worker.py

# Terminal 2
uv run langgraph_plugin/graph_api/human_in_the_loop/run_workflow.py

The LangSmith Tracing samples bundle the Worker and Workflow execution into a single main.py:

uv run langgraph_plugin/<api>/langsmith_tracing/main.py

Key Features Demonstrated

• Durable execution -- Every graph node / @task runs in a Workflow or as a Temporal activity with configurable timeouts and retry policies.
• Human-in-the-loop -- LangGraph's interrupt() pauses the graph; Temporal signals deliver human input; queries expose pending state to UIs.
• Continue-as-new with caching -- cache() captures completed task results; passing the cache to the next execution avoids re-running them.
• Conditional routing -- Graph API's add_conditional_edges and Functional API's native if/else/while for agent loops.
• Parallel execution -- Functional API launches multiple tasks concurrently by creating futures before awaiting them.
• Streaming -- Workflow Streams expose a durable, offset-addressed event channel that external clients subscribe to while the workflow is still running. Nodes emit fine-grained tokens via get_stream_writer() (routed by the plugin's streaming_topic), and the workflow can publish coarse astream progress to its own topic.

Related

• Temporal LangGraph plugin docs