Conductor Agent Python SDK

Build durable Python AI agents on Conductor. Agents can use local Python tools, wait for people, execute dynamic plans, and recover after process restarts because Conductor persists execution state.

Install

pip install 'conductor-python[agents]'

Requirements: Python 3.10+ and a Conductor server with an LLM provider configured server-side. Replace example model names with a model enabled on that server.

Start here

• Getting started — configure a server and run a basic agent.
• Deploy · Serve · Run · Plan — choose a runtime mode.
• Scheduling — manage deployed-agent schedules.

Build agents

• Agents, tools, and multi-agent
• Guardrails, termination, callbacks
• Stateful agents, streaming and HITL, and structured output

Framework bridges

• Google ADK, LangChain, and LangGraph
• OpenAI Agents SDK and Claude Agent SDK

Operate and inspect

• Runtime reference, control-plane reference, and API map
• Agent-definition fields and configuration contract

What Conductor adds

Capability	Conductor agent runtime
Process recovery	Durable workflow state resumes from completed work.
Python tools	Tools run as independently scalable Conductor worker tasks.
Long-running work	Human approval, schedules, and events do not occupy application threads.
Dynamic execution	Plans become durable, inspectable sub-workflows.
Observability	Inputs, outputs, tool calls, retries, and status share one execution record.