Conductor

Active
GitHub Java Apache-2.0

Description

An event-driven agentic orchestration platform providing a durable and highly resilient execution engine for applications and AI agents.

Key Features

  • Durable Execution — Every step persisted; survives crashes, restarts, and network failures with configurable retries
  • Dynamic Workflows — Runtime-resolved dynamic forks, tasks, and sub-workflows; LLMs generate JSON workflow definitions
  • AI Agent Orchestration — 14+ native LLM providers, MCP tool calling, function calling, and human-in-the-loop approval
  • Full Replayability — Restart from beginning, rerun from any task, or retry only the failed step at any time
  • Polyglot Workers — Workers in Java, Python, Go, JavaScript, C#, Ruby, or Rust; poll, execute, and report
  • Self-hosted, No Lock-in — Apache 2.0; 5 persistence backends, 6 message brokers; runs anywhere Docker or JVM runs

Use Cases

💡 Orchestrate complex business processes across multiple microservices like order fulfillment and payment processing
💡 Build autonomous AI agent loops that discover tools via MCP, reason with LLMs, and execute tools until completion
💡 Orchestrate AI/ML pipelines with multi-stage workflows including data preprocessing, training, evaluation, and deployment
💡 Implement long-running processes requiring durable persistence and reliable retries like data migration and report generation
💡 Orchestrate internet-scale distributed tasks at Netflix, Tesla, LinkedIn, and J.P. Morgan production workloads

Strengths & Limitations

Strengths

  • Actively maintained, recent updates
  • High community interest (32.1k stars)
  • Permissive open-source license (Apache-2.0)
  • Established track record (2 years in production)

Categories

Quick Start

npm install -g @conductor-oss/conductor-cli
conductor server start
# Open http://localhost:8080

# Run your first workflow
curl -s https://raw.githubusercontent.com/conductor-oss/conductor/main/docs/quickstart/workflow.json -o workflow.json
conductor workflow create workflow.json
conductor workflow start -w hello_workflow --sync

Related Projects

Hatchet

7.7k · Go
Active A+

🪓 An orchestration engine for background tasks, AI agents, and durable workflows.

workfloworchestrationdurable-execution +1
  • · Durable Workflows — fault-tolerant long-running tasks with pause/resume, event waits, and automatic recovery from failure
  • · DAG Orchestration — build data pipelines and complex workflows with directed acyclic graph support
  • · Multi-Language SDKs — first-class support for Python, TypeScript, Go, and Ruby applications

Temporal

22.3k · Go
Active A

Temporal is a distributed durable execution platform that turns agent workflows from ad-hoc scripts into observable production systems through automatic retries and state management.

workflowdurable-executionorchestration +2
  • · Durable workflow execution — workflows are event-sourced and resumable from any point after a crash
  • · Automatic retries and timeouts — built-in configurable retry policies, timeouts, and exponential backoff
  • · Multi-language SDKs — official SDKs for Go, Java, TypeScript, Python, .NET, PHP and more

Agent Orchestrator

9.6k · Go
Active A

An agentic orchestrator for parallel coding agents that plans tasks, spawns agents, and autonomously handles CI fixes, merge conflicts, and code reviews for complex development workflows.

orchestrationparallel-agentscode-review +3
  • · Spawns parallel coding agents in isolated git worktrees with independent branches and PRs
  • · Agent-agnostic: works with Claude Code, Codex, Aider, and others
  • · Runtime-agnostic: supports tmux, ConPTY/process, and Docker

Mission Control

4.1k · TypeScript
Active A

AI Agent Orchestration Dashboard for managing AI agents, assigning tasks, and coordinating multi-agent collaboration.

orchestrationdashboardmulti-agent +1
  • · Work orchestration: manage organizations, board groups, boards, tasks, and tags in a unified interface
  • · Agent operations: create, inspect, and manage agent lifecycle from a single control surface
  • · Governance and approvals: route sensitive actions through explicit approval flows with decision trails