These samples demonstrate the Temporal Deep Agents plugin, which makes LangChain Deep Agents durable. Build your agent with create_deep_agent(...) inside a @workflow.defn and add DeepAgentsPlugin() to your client — each LLM call and each I/O tool/backend operation becomes a Temporal Activity, while the agent's control loop runs (and deterministically replays) inside the Workflow.

Experimental. The temporalio.contrib.deepagents plugin is experimental and its API may change.

DeepAgentsPlugin is a client-level plugin: add it to Client.connect(...) and the SDK propagates it to any Worker built from that client. Add it on exactly one side.

Python ≥ 3.11 required. deepagents (and therefore the plugin) does not support older interpreters. On Python 3.10 the deepagents dependency group resolves to nothing, so uv sync silently installs none of the dependencies below.

1. Install dependencies:

   uv sync --group deepagents

   The temporalio-contrib-deepagents plugin is experimental and not yet published to PyPI, so it is not part of the deepagents group above. Until it publishes, install it from a local checkout of the SDK (adjust the path to wherever your sdk-python checkout lives):

   uv pip install ../sdk-python/temporalio/contrib/deepagents

   The plugin uses a namespace-package overlay layout, so install it non-editable (no -e) — an editable install cannot map its sources onto temporalio.contrib.deepagents. Once it is on PyPI this step goes away and you can add temporalio-contrib-deepagents to the deepagents group.

2. Configure a model provider. The samples use anthropic:claude-sonnet-4-5, which needs an Anthropic API key:

   export ANTHROPIC_API_KEY=...

   To use a different provider, change the model= string in the sample's workflow.py and set that provider's credentials (the plugin resolves the model worker-side via LangChain's init_chat_model).

3. Start a Temporal dev server:

   temporal server start-dev

Use uv run --no-sync. Because the experimental plugin is installed out-of-band (uv pip install … above) and is not in any dependency group, a bare uv run or uv sync re-syncs the environment to the lockfile first and uninstalls it. --no-sync runs against the environment as-is. (Once the plugin publishes and joins the deepagents group, the flag is unnecessary.)

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

# Terminal 1: start the Worker
uv run --no-sync deepagents_plugin/<sample>/run_worker.py

# Terminal 2: start the Workflow
uv run --no-sync deepagents_plugin/<sample>/run_workflow.py

For example, to run the hello world sample:

# Terminal 1
uv run --no-sync deepagents_plugin/hello_world/run_worker.py

# Terminal 2
uv run --no-sync deepagents_plugin/hello_world/run_workflow.py

The langsmith_tracing sample instead bundles the worker and starter into a single driver:

uv run --no-sync deepagents_plugin/langsmith_tracing/main.py

• Durable model invocation — every LLM call runs in an invoke_model activity with configurable timeouts and retries; a bare model= string is auto-routed, or use create_temporal_deep_agent(..., activity_options=...) to scope model-call options per agent (recommended).
• Explicit Workflow-vs-Activity tool choice — activity_as_tool, tool_as_activity, and TemporalBackend move I/O out of workflow code.
• Human-in-the-loop — the native LangGraph interrupt_on return value mapped to a Temporal Query and Update.
• Long-lived agents — run_deep_agent(...) carries messages and the result cache across server-suggested (or explicitly thresholded) continue-as-new.
• Sub-agent durability — sub-agents inherit the durable model object with no extra wiring.
• Streaming — forward model chunks to external subscribers while keeping the durable result unchanged.
• Observability — compose with LangSmithPlugin for tracing.

• Temporal Deep Agents plugin
• LangChain Deep Agents
• langgraph_plugin — for agents built directly as LangGraph graphs