Orkes Conductor

Battle Tested Platform for Agent and Workflow Orchestration

Orchestrate agents, services and human decisions in one durable execution. Keep your code and frameworks. Conductor handles the state, coordination and recovery.

Start for free
See how it works
Example workflow Production deployment One Conductor execution
  1. Agent decision Plan the deployment Selects the deployment tool
  2. Required human approval Approve the release Execution waits for approval
  3. Defined service call Deploy the service Runs your existing deployment code

Execution state saved at every step

Built on Conductor
Created at Netflix
Open source at the core.
100,000+ Orkes developers
1,200+ Companies using Conductor
32,000+ GitHub stars

Developer first

Build agents and workflows your way.

Use your coding agent with Conductor Skills, write with SDKs or build in the visual editor. Keep your existing services and agent frameworks.

Conductor Skills

Build with your coding agent.

Build, run and debug workflows, agents and workers from Claude Code, Codex, Cursor and other coding agents.

Get Conductor Skills
Example prompt

Build a deployment agent that requires human approval before deploying payments-api.

Python · code excerpt
from conductor.ai.agents import (
    Agent, AgentRuntime, tool
)

@tool(approval_required=True)
def deploy_to_production(service, version):
    # Your existing deployment function.
    return rollout(service, version)

agent = Agent(
    name="production_deploy_agent",
    model="openai/gpt-4o-mini",
    tools=[deploy_to_production],
    instructions="Deploy requested releases.",
)

with AgentRuntime(config) as runtime:
    runtime.deploy(agent)
    runtime.start(
        agent, "Deploy payments-api v2.4.1"
    )
    runtime.serve(agent)
Conductor execution view From agent decision to deployment.
Conductor execution graph for a production deployment agent, showing the model call, human approval, deployment tool with two attempts, and final result.

The execution graph records agent turns, tool calls, approvals and retries.

Work in your language.

Build with Python, Java, JavaScript / TypeScript, Go or C#.

Explore the SDKs

Build or bring your agents.

Use the Conductor Agent SDK, or bring agents built with LangGraph, OpenAI Agents SDK or Google ADK. Agents and workflows can call each other.

Bring your agent

Bring determinism to your agents.

The agent selects the deployment tool. The approval rule in your code controls when that tool can run.

Durable execution

A failed step doesn’t erase the work.

Conductor saves execution state as work progresses. Retry a failed task or rerun from a chosen step using the outputs already recorded.

Long-running processes can wait for a human, an event or an external system, then continue with their state intact.

Explore execution and recovery
Interactive example Production deployment
Service timed out
  1. Plan the deployment Agent decision recorded
  2. Approve the release Human approval recorded
  3. Deploy the service Retry after the service is available

Earlier steps and their results stay in place.

Orkes execution timeline with task durations and the Orkes Assistant alongside it.
Execution history and the Orkes Assistant, together in Conductor.

Visibility and control

Understand the execution.
Act on what you find.

Inspect inputs, outputs, agent decisions and tool calls in one execution history. Use the Orkes Assistant to explain failures and suggest fixes.

See the Orkes Assistant

Proven in production.

Built on Conductor, originally created and open sourced at Netflix. Orkes adds the governance, operational capabilities and support teams need for business-critical agents and workflows.

Govern every execution.

Manage access with RBAC and SSO. Keep secrets out of code, require approvals and retain audit trails across agents and workflows.

Build on an open foundation.

Conductor and its SDKs are open source. Build with your languages and services, with the visibility and control of Orkes Conductor.

Explore Conductor OSS

Work with the team behind Conductor.

Get enterprise support and guidance from Orkes, from your first deployment through ongoing production operations.

Explore Orkes Cloud
LinkedIn
Agents in production

LinkedIn runs its agent platform on Conductor.

Agents save progress, pause for human approval and hand work to other agents on the same durable execution engine.

Obi Azogu Senior Staff Software Engineer, LinkedIn
How LinkedIn uses Conductor
Twilio Segment
54,000 concurrent workflows
“We stopped maintaining a workflow engine and started building on one.”
Joe Yan Staff Software Engineer, Twilio Segment
How Twilio Segment uses Conductor
Bumble
Trust and safety

Seven handoffs.
One Conductor workflow.

Bumble runs trust-and-safety reports through Conductor, combining AI steps and human moderation with automatic retries and recorded decisions.

Paul Vander Griend Distinguished Engineer, Bumble
How Bumble uses Conductor

Orkes Conductor

Build agents and workflows your business can depend on.

Start building for free, or see Conductor in action with your team.

Start for free
Conductor execution view
Complete Conductor production deployment execution graph