Conductor

What it does

Agent frameworks

The site says users can bring agents from LangGraph, CrewAI, Google ADK, and the OpenAI SDK.checked 7 Oct 2026

AI capabilities

Conductor provides native LLM tasks, MCP tool discovery and calls, human approval, and vector workflows for retrieval-augmented generation.checked 7 Oct 2026

Deployment

The project documents self-hosting with Docker and says Conductor runs anywhere Docker runs.checked 7 Oct 2026

Durable execution

Conductor persists workflow and task state and supports recovery after worker or infrastructure failure, retries, timeouts, pause, resume, and termination.checked 7 Oct 2026

Integrations

The integration guide describes event-driven orchestration, MCP tool integration, and Agent2Agent integration with independently deployed agents.checked 7 Oct 2026

Intended users

The FAQ says Conductor is designed for developers who write code, with workers and tasks built in a preferred programming language.checked 7 Oct 2026

Languages

The project lists SDKs for Java, Python, TypeScript, .NET, Go, Ruby, and Rust.checked 7 Oct 2026

License

Conductor is Apache 2.0 licensed and can be self-hosted on your own infrastructure.checked 7 Oct 2026

Storage

Conductor uses Redis by default and Elasticsearch for indexing, and its storage layers can be replaced with alternative backends and queue providers.checked 7 Oct 2026

Support

The project directs users to its public Slack community to ask questions and share resources.checked 7 Oct 2026

What it does

Conductor is an open-source platform for building and orchestrating AI agents and workflows on a durable execution engine.checked 7 Oct 2026

Workflow scale

The documentation says Conductor supports nested loops, dynamic branching, sub-workflows, and workflows with thousands of tasks.checked 7 Oct 2026