---
id: conductor-python
version: "2.0.0"
license: Apache-2.0
license_treatment: permissive
maintenance: active
---

# conductor-python — Python SDK for working with https://github.com/conductor-oss/conductor

License: permissive · Maintenance: active · Downloads: 154.9K/mo

## What it is and what it does

Conductor-python is a client SDK for the Conductor workflow orchestration engine, enabling you to define and execute durable agents, workflows, and distributed workers in Python. It abstracts away the complexity of managing retries, state persistence, and observability—Conductor handles those concerns server-side while your Python code runs as stateless tasks or agents. The SDK supports both traditional workflow-and-worker patterns (where you define a DAG and run independent Python workers) and modern AI agent patterns (with LLM reasoning, tools, guardrails, and human approval).

The package includes clients for workflows, tasks, workers, metadata, scheduling, and metrics, plus optional framework bridges to integrate existing Google ADK, LangChain, LangGraph, OpenAI Agents, or Claude Agent SDK agents into Conductor's durability model. You connect to a Conductor server—either a local instance via CLI or Docker, or the hosted Orkes Developer Edition—and the SDK handles communication, task polling, and result reporting.

Use it for:

- Build AI agents that survive process crashes by storing execution state server-side and resuming from completed work.
- Coordinate long-running multi-step workflows (data pipelines, approval chains) without holding application threads open.
- Scale Python workers independently while Conductor manages task distribution, retries, and delivery guarantees.
- Integrate an existing LangChain or LangGraph agent into a durable orchestration layer without rewriting it.
- Implement human-in-the-loop workflows where approval steps pause execution and resume after human decision.

## Worth the install?

AI-flagged interpretation of the facts above — verify before relying.

Build durable Conductor agents, workflows, and workers in Python, with the Conductor server managing retries, state, and observability across distributed execution.

Yes. Active maintenance, low install friction, permissive license, and no known vulnerabilities. Install if you need durable workflow orchestration, distributed task execution, or want to add durability to an existing AI agent framework. Requires a Conductor server (free Developer Edition available) and Python 3.10+.

## Install

pip install conductor-python
uv add conductor-python
poetry add conductor-python

## Installing conductor-python

Before you install: Low friction: pure Python wheel with 14 runtime dependencies, all common libraries. Actively maintained with a release 11 days ago. Supports Python 3.10 through 3.14.

License in practice: Apache-2.0 permissive license allows commercial and private use with minimal restrictions; attribution required.

Quickstart:

pip install conductor-python

from conductor.client.workflow.conductor_workflow import ConductorWorkflow
from conductor.client.configuration.configuration import Configuration

config = Configuration(server_url='http://localhost:8080/api')
workflow = ConductorWorkflow(name='hello')
# Define tasks and execute

Requires a running Conductor server (local via CLI/Docker or hosted Orkes Developer Edition) and Python 3.10+.

Verify before relying:

- Whether framework bridges (Google ADK, LangChain, LangGraph, OpenAI Agents, Claude) are included in base install or require separate extras.
- Performance characteristics and scalability limits for worker count and task throughput.
- Whether the SDK supports workflow versioning and zero-downtime deployment patterns.

## Package facts

- License: Apache-2.0 (permissive)
- Python support: supports_current
- Install friction: low
- Maintenance: active
- Downloads: 154.9K/month (top 15,000 on PyPI)
- Known vulnerabilities: none known

## Tags

durable workflow orchestration python, conductor agent framework, distributed task execution python, workflow state management, ai agent with durability, python worker coordination, long-running process orchestration, workflow-orchestration, distributed-computing, ai-agents

[View on SkillFed](https://skillfed.io/packages/conductor-python) · [View on PyPI](https://pypi.org/project/conductor-python/)