These samples demonstrate the Temporal Claude Agent SDK integration, which runs Claude Code agents as Temporal Workflows. You write ordinary Claude Agent SDK code in a Workflow, and Claude Code runs unmodified. If a Worker fails, the agent picks up where it left off, and approvals, hooks, and custom tools run as durable Workflow code.
| Category | Sample | What it shows |
|---|---|---|
| Agent Chat | agent_chat | A multi-turn chat driven by Updates, with Continue-As-New that resumes Claude's session in the next run. Start here. |
| Tools | tools | One custom tool computed in the Workflow and one that runs an Activity, both via @tool and create_sdk_mcp_server. |
| Streaming | streaming | Token-by-token output through a Workflow Stream, with or without a subscriber. |
| Hooks | hooks | A PreToolUse hook that blocks Bash commands that delete files and records each one through an Activity. |
| Human in the Loop | human_in_the_loop | can_use_tool waits durably for a person's Update: approve, deny, or cancel. |
| Structured Output | structured_output | A JSON-schema result validated as a Pydantic model at the Workflow boundary. |
| Fork Session | fork_session | One conversation forked with fork_session into parallel branches, each with a session ID from Claude Code. |
| Multi-Agent | multi_agent | Claude Code's native subagents: a coordinator delegating to a researcher and a writer. |
| Plugin with Custom Transport | plugin_with_custom_transport | A Claude Code plugin with a skill and an MCP server, copied into a Docker Sandbox (sbx) by a custom connector that runs Claude Code there. |
| Observability | open_telemetry | One OpenTelemetry trace across the caller, the Workflow, its Activities, and Claude Code's model and tool spans. |
Most samples run Claude Code as a subprocess of the Worker. plugin_with_custom_transport runs it in a Docker Sandbox instead.
Every sample finishes its turn if its Worker stops mid-turn. The Workflow resumes the session at the turn's prompt and sends "Continue from where you left off.", the message Claude Code itself sends to continue an interrupted turn. Claude Code then redoes the turn. human_in_the_loop remembers each decision, so the redone turn doesn't ask again for a tool call a person already decided.
The next Worker needs the session. The subprocess samples keep it on the Worker's host, and plugin_with_custom_transport keeps it in its sandbox on the Worker's machine.
Install the Temporal CLI, then the dependencies:
uv sync --group claude-agent-sdkThe claude-agent-sdk package bundles Claude Code, so you don't need to install it separately. Each sample's README has the commands to run it.
The tests run every sample against the scripted API and a local dev server, with no credentials or Docker:
uv run --group claude-agent-sdk pytest tests/claude_agent_sdk_pluginThey're skipped on Windows, where the default transport's shell scripts don't run.