Verified project record

conductor-oss/conductor

A workflow and agent orchestration engine that separates orchestration from business logic, persisting every execution step so processes survive crashes and restarts. It scales horizontally to billions of executions and supports workers written in Java, Python, Go, JavaScript, C#, Ruby, or Rust.

Project overview

Project type: AI Agent · Workflow
Use cases: Automation
Deployment: Refer to project documentation
License: Apache-2.0

Best for

Developers and enterprise teams who need to orchestrate distributed systems or AI agents at scale while keeping orchestration logic separated from business logic.

Key capabilities

Every step is persisted, surviving crashes, restarts, and network failures with configurable retries and timeouts.
Orchestration is separated from business logic so determinism is architectural; workers run any code and the workflow graph stays deterministic by construction.
Orchestrates AI agents with native integrations for 14+ LLM providers, function calling, human-in-the-loop approval, and vector databases for RAG.
Supports workers written in Java, Python, Go, JavaScript, C#, Ruby, or Rust without SDK lock-in or determinism constraints.
Supports dynamic forks, tasks, and sub-workflows resolved at runtime, enabling LLMs to generate and execute JSON workflow definitions immediately.
Restart workflows from the beginning, rerun from any task, or retry just the failed step, preserving full execution history indefinitely.
Scales horizontally to billions of workflow executions, battle-tested at Netflix, Tesla, LinkedIn, and J.P. Morgan.
Provides a visual UI for designing, running, and debugging workflows with full observability of inputs, outputs, timing, and retry history.

Limitations and risks

The CLI quick start path requires Node.js v16+ and Java 21+ to be installed.
Building from source requires Docker Desktop, Java (JDK) 21+, Node.js 18+, and pnpm.

Getting started

Install via npm using `npm install -g @conductor-oss/conductor-cli` and open `http://localhost:8080` to access the UI.

Evidence and sources

GitHub project description: Conductor is an event driven agentic workflow engine providing durable and highly resilient execution engine for applications and AI Agents
README: Conductor - Internet scale Agentic Workflow Engine
README: Trusted in production at Netflix, Tesla, LinkedIn, and J.P. Morgan. Actively maintained by [Orkes](https://orkes.io) and a growing [community](https://join.slack.com/t/orkes-condu…
README: Conductor pioneered durable execution patterns, ensuring workflows and durable agents complete reliably despite infrastructure failures or crashes. Every step is persisted and rec…
README: Conductor is an open-source, durable workflow engine built at [Netflix](https://netflixtechblog.com/netflix-conductor-a-microservices-orchestrator-2e8d4771bf40) for orchestrating…

Reviewed at: 2026-07-16T19:14:21Z