Logo
Deploy Now

SaaS Alternative

Apache Airflow AWS Step Functions

Categories

DevOps Automation Data Pipeline Microservices Workflow Orchestration Task Queue AI Agent Platform

Stars

32,102

Forks

993

Watchers

48

Developer links

Last Updated: 08-21-2026 02:57 PM (UTC)

Conductor

Originally built at Netflix to orchestrate microservices powering 230 million subscribers and now trusted in production at Tesla, LinkedIn, and J.P. Morgan, Conductor is the most battle-tested open-source workflow engine available — with 32,000 GitHub stars and horizontal scalability to billions of executions. The architecture cleanly separates orchestration from business logic: workflows are defined in declarative JSON while workers execute tasks in any of seven supported languages (Java, Python, Go, JavaScript, C#, Ruby, Rust) with zero framework constraints. Durable execution persists every state transition, enabling automatic retries, configurable timeouts, crash recovery, and instant replay from any failure point without re-executing completed tasks. Native AI agent orchestration supports 14+ LLM providers (Anthropic, OpenAI, Google Gemini, AWS Bedrock, Mistral, Cohere, HuggingFace, Ollama), MCP tool calling, function calling, human-in-the-loop approval gates, and vector database integration (Pinecone, pgvector, MongoDB Atlas) for RAG pipelines. Deploy with your choice of five persistence backends (PostgreSQL, Redis, MySQL, Cassandra, SQLite), six message brokers, and Elasticsearch or OpenSearch for workflow indexing — all configurable via Docker Compose files included in the repository. The built-in web UI provides workflow visualization, execution monitoring, task queue inspection, and manual intervention controls. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache-2.0 licensed.

Conductor
Conductor
Conductor
Conductor
Conductor

Benefits

  • Netflix-Scale Reliability Built In
  • Durable execution persists every state transition with automatic retries, configurable timeouts, and crash recovery that resumes workflows from the exact failure point without repeating work.
  • Native AI Agent Orchestration
  • Built-in task types for 14+ LLM providers with MCP tool calling, function calling, human-in-the-loop approval gates, and vector database integration for RAG pipelines.
  • Polyglot Workers, Zero Lock-In
  • Workers execute in Java, Python, Go, JavaScript, C#, Ruby, or Rust with no framework constraints — plain functions polling a task queue over HTTP.
  • Flexible Persistence Stack
  • Choose from PostgreSQL, Redis, MySQL, Cassandra, or SQLite for storage combined with Elasticsearch or OpenSearch for indexing — all swap at runtime via configuration.

Features

  • Durable Execution
  • Persists workflow state across crashes with at-least-once delivery, automatic retries, timeout handling, and full replayability from any task.
  • Visual Workflow Builder
  • Built-in web UI renders workflow DAGs, monitors execution progress in real time, inspects task queues, and enables manual retry or restart operations.
  • Dynamic Workflows
  • Runtime task generation with branching, loops, forks, joins, sub-workflows, and conditional logic defined in JSON or code-first SDK syntax.
  • LLM Integration
  • Native task types connect to Anthropic, OpenAI, Gemini, Bedrock, Mistral, Cohere, and Ollama with structured output parsing and streaming support.
  • Event-Driven Architecture
  • Supports six message brokers including Kafka, RabbitMQ, AWS SQS, NATS, and AMQP for event-triggered workflow execution and inter-workflow communication.