Conductor OSS
Conductor OSS is the Netflix-founded, Orkes-stewarded open source workflow and agentic AI orchestration platform. It provides a durable, event-driven workflow engine for coordinating microservices, long-running tasks, human approvals, and LLM-powered agents across any language or cloud, with first class support for HTTP, gRPC, Kafka, AMQP, SQS, and MCP-based tool calling.
2 APIs
7 Features
Agentic AIDurable ExecutionEvent-DrivenMicroservicesNetflixOpen SourceOrchestrationWorkflow EngineWorkflows
Durable Workflow Execution
Workflow state is persisted at every step so executions survive worker restarts, server failover, and long human-in-the-loop waits.
Polyglot Workers
Tasks are executed by language-agnostic workers that poll the server, with official SDKs in Java, Python, Go, JavaScript / TypeScript, C#, Clojure, Ruby, and Rust.
System Tasks and Operators
Built-in HTTP, Kafka, JQ, wait, human approval, sub-workflow, fork, join, switch, do-while, and dynamic-fork operators compose workflows without writing code.
Agentic AI and LLM Orchestration
Native LLM tasks for 14+ providers, vector database integrations for RAG, MCP tool calling, and human-in-the-loop checkpoints make Conductor a runtime for agentic AI applications.
Event-Driven Triggers
Event handlers consume from Kafka, AMQP, SQS, NATS, and webhook sources to start workflows or complete tasks from external systems.
Horizontal Scalability
Stateless API servers and worker pools scale horizontally, with pluggable persistence (PostgreSQL, MySQL, Cassandra, Redis) and indexing (OpenSearch / Elasticsearch).
Operational Observability
Built-in metrics, structured logs, distributed tracing, and a Swagger UI on every server expose the workflow surface for operators.
Microservices Orchestration
Coordinate sagas, compensations, retries, and timeouts across distributed microservices without bespoke orchestration code.
AI Agent Orchestration
Run production-grade agentic workflows with reasoning loops, tool calling, MCP integration, RAG retrieval, and human approvals.
Payment and Order Processing
Reliable long-running flows for payments, fulfillment, KYC, and onboarding — the reference example workload shipped by Conductor.
Data and ML Pipelines
Schedule and orchestrate ETL, model training, and inference pipelines with durable retries and conditional branching.
Human-in-the-Loop Approvals
Pause workflows on human tasks, capture approvals via UI or API, and resume execution deterministically.
Event-Driven Integration
Bridge message brokers and SaaS webhooks into deterministic workflows across the enterprise.
Apache Kafka
System task and event-handler integration for Kafka topics.
AMQP / RabbitMQ
Built-in AMQP system task and event source.
AWS SQS
Native SQS event queue and system task module.
NATS
NATS event queue integration for triggering workflows.
PostgreSQL / MySQL / Cassandra / Redis
Pluggable persistence backends for workflow and task state.
OpenSearch / Elasticsearch
Pluggable indexing backends powering search and history.
AWS S3 / Azure Blob
External payload storage for large workflow inputs and outputs.
Model Context Protocol (MCP)
Official MCP server exposes Conductor to AI agents as tools.
gRPC
gRPC API surface alongside the REST API for high-performance clients.
Conductor OSS
Apache 2.0 open source workflow engine, self-hosted via Docker, Helm, or source build.
Orkes Developer Edition
Free hosted Conductor sandbox by Orkes with all enterprise features enabled for prototyping and learning.
Orkes Enterprise / Cloud
Fully managed Conductor on AWS, Azure, GCP, or on-prem with SOC2, RBAC, SSO, audit logs, and up to 99.99% availability SLA.
aid: conductor-oss
name: Conductor OSS
description: >-
Conductor OSS is the Netflix-founded, Orkes-stewarded open source workflow and agentic AI orchestration platform. It
provides a durable, event-driven workflow engine for coordinating microservices, long-running tasks, human approvals,
and LLM-powered agents across any language or cloud, with first class support for HTTP, gRPC, Kafka, AMQP, SQS, and
MCP-based tool calling.
type: Index
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
tags:
- Agentic AI
- Durable Execution
- Event-Driven
- Microservices
- Netflix
- Open Source
- Orchestration
- Workflow Engine
- Workflows
url: https://raw.githubusercontent.com/api-evangelist/conductor-oss/refs/heads/main/apis.yml
created: '2026-05-25'
modified: '2026-05-25'
specificationVersion: '0.19'
apis:
- aid: conductor-oss:conductor-oss-rest-api
name: Conductor OSS REST API
description: >-
The Conductor OSS REST API is the canonical control plane for the workflow engine — registering and versioning
workflow and task definitions, starting and querying workflow executions, polling and updating tasks from workers,
and wiring external event sources into workflows. It is served by the Conductor Server (Java / Spring Boot) and is
the same surface used by every official Conductor SDK and the Orkes-hosted Conductor Cloud.
humanURL: https://docs.conductor-oss.org/
baseURL: http://localhost:8080/api
tags:
- Agentic AI
- Durable Execution
- Event-Driven
- Microservices
- Open Source
- Orchestration
- Workflow Engine
- Workflows
properties:
- type: Documentation
url: https://docs.conductor-oss.org/
- type: APIReference
url: https://docs.conductor-oss.org/reference
- type: Quickstart
url: https://docs.conductor-oss.org/getting-started
- type: Authentication
url: https://docs.conductor-oss.org/devguide/running/configuration/security
- type: OpenAPI
url: >-
https://raw.githubusercontent.com/api-evangelist/conductor-oss/refs/heads/main/openapi/conductor-oss-openapi.yml
- aid: conductor-oss:conductor-mcp
name: Conductor MCP Server
description: >-
Conductor MCP is an official Model Context Protocol server for Orkes Conductor that exposes workflow execution,
task management, and metadata operations as MCP tools so that LLMs and AI agents can orchestrate Conductor
workflows directly.
humanURL: https://github.com/conductor-oss/conductor-mcp
tags:
- Agentic AI
- MCP
- Open Source
- Orchestration
- Tools
properties:
- type: GitHubRepository
url: https://github.com/conductor-oss/conductor-mcp
- type: Documentation
url: https://docs.conductor-oss.org/ai-cookbook
common:
- type: Website
url: https://conductor-oss.org/
- type: Documentation
url: https://docs.conductor-oss.org/
- type: GettingStarted
url: https://docs.conductor-oss.org/getting-started
- type: GitHub
url: https://github.com/conductor-oss
- type: GitHubOrganization
url: https://github.com/conductor-oss
- type: GitHubRepository
url: https://github.com/conductor-oss/conductor
- type: Blog
url: https://orkes.io/blog/
- type: Slack
url: https://join.slack.com/t/orkes-conductor/shared_invite/zt-3dpcskdyd-W895bJDm8psAV7viYG3jFA
- type: YouTube
url: https://www.youtube.com/@orkesio
- type: License
url: https://github.com/conductor-oss/conductor/blob/main/LICENSE
- type: Pricing
url: https://orkes.io/pricing
- type: Portal
url: https://cloud.orkes.io/
- type: SignUp
url: https://cloud.orkes.io/signup
- type: Training
url: https://orkes.io/academy/
- type: SDK
url: https://github.com/conductor-oss/java-sdk
- type: SDK
url: https://github.com/conductor-oss/python-sdk
- type: SDK
url: https://github.com/conductor-oss/go-sdk
- type: SDK
url: https://github.com/conductor-oss/javascript-sdk
- type: SDK
url: https://github.com/conductor-oss/csharp-sdk
- type: SDK
url: https://github.com/conductor-oss/clojure-sdk
- type: SDK
url: https://github.com/conductor-oss/rust-sdk
- type: SDK
url: https://github.com/conductor-oss/ruby-sdk
- type: CLI
url: https://github.com/conductor-oss/conductor-cli
- type: Features
data:
- name: Durable Workflow Execution
description: >-
Workflow state is persisted at every step so executions survive worker restarts, server failover, and long
human-in-the-loop waits.
- name: Polyglot Workers
description: >-
Tasks are executed by language-agnostic workers that poll the server, with official SDKs in Java, Python, Go,
JavaScript / TypeScript, C#, Clojure, Ruby, and Rust.
- name: System Tasks and Operators
description: >-
Built-in HTTP, Kafka, JQ, wait, human approval, sub-workflow, fork, join, switch, do-while, and dynamic-fork
operators compose workflows without writing code.
- name: Agentic AI and LLM Orchestration
description: >-
Native LLM tasks for 14+ providers, vector database integrations for RAG, MCP tool calling, and
human-in-the-loop checkpoints make Conductor a runtime for agentic AI applications.
- name: Event-Driven Triggers
description: >-
Event handlers consume from Kafka, AMQP, SQS, NATS, and webhook sources to start workflows or complete tasks
from external systems.
- name: Horizontal Scalability
description: >-
Stateless API servers and worker pools scale horizontally, with pluggable persistence (PostgreSQL, MySQL,
Cassandra, Redis) and indexing (OpenSearch / Elasticsearch).
- name: Operational Observability
description: >-
Built-in metrics, structured logs, distributed tracing, and a Swagger UI on every server expose the workflow
surface for operators.
- type: UseCases
data:
- name: Microservices Orchestration
description: >-
Coordinate sagas, compensations, retries, and timeouts across distributed microservices without bespoke
orchestration code.
- name: AI Agent Orchestration
description: >-
Run production-grade agentic workflows with reasoning loops, tool calling, MCP integration, RAG retrieval, and
human approvals.
- name: Payment and Order Processing
description: >-
Reliable long-running flows for payments, fulfillment, KYC, and onboarding — the reference example workload
shipped by Conductor.
- name: Data and ML Pipelines
description: >-
Schedule and orchestrate ETL, model training, and inference pipelines with durable retries and conditional
branching.
- name: Human-in-the-Loop Approvals
description: Pause workflows on human tasks, capture approvals via UI or API, and resume execution deterministically.
- name: Event-Driven Integration
description: Bridge message brokers and SaaS webhooks into deterministic workflows across the enterprise.
- type: Integrations
data:
- name: Apache Kafka
description: System task and event-handler integration for Kafka topics.
- name: AMQP / RabbitMQ
description: Built-in AMQP system task and event source.
- name: AWS SQS
description: Native SQS event queue and system task module.
- name: NATS
description: NATS event queue integration for triggering workflows.
- name: PostgreSQL / MySQL / Cassandra / Redis
description: Pluggable persistence backends for workflow and task state.
- name: OpenSearch / Elasticsearch
description: Pluggable indexing backends powering search and history.
- name: AWS S3 / Azure Blob
description: External payload storage for large workflow inputs and outputs.
- name: Model Context Protocol (MCP)
description: Official MCP server exposes Conductor to AI agents as tools.
- name: gRPC
description: gRPC API surface alongside the REST API for high-performance clients.
- type: Solutions
data:
- name: Conductor OSS
description: Apache 2.0 open source workflow engine, self-hosted via Docker, Helm, or source build.
- name: Orkes Developer Edition
description: Free hosted Conductor sandbox by Orkes with all enterprise features enabled for prototyping and learning.
- name: Orkes Enterprise / Cloud
description: >-
Fully managed Conductor on AWS, Azure, GCP, or on-prem with SOC2, RBAC, SSO, audit logs, and up to 99.99%
availability SLA.
maintainers:
- FN: Kin Lane
email: kin@apievangelist.com