Orcheo¶

Orcheo is a workflow orchestration platform designed for vibe coding — AI coding agents like Claude Code can start services, build workflows, and deploy them for you automatically.

Note

This project is currently in Beta. Expect breaking changes as we iterate rapidly towards 1.0.

Why Orcheo?¶

Vibe-coding-first: Already using Claude Code, Codex CLI, or Cursor? You don't need to learn Orcheo. Install the agent skill and let your AI agent handle setup, workflow creation, and deployment.
Python-native: Workflows are Python code powered by LangGraph — no proprietary DSL to learn.
CLI-first: Manage everything via the orcheo CLI (or horcheo for human-readable output) — install, configure, deploy, and run workflows from the terminal. The GUI is optional.

Quick Start¶

Use the installation path that matches your setup:

Prerequisite: Docker Desktop/Engine must be installed to run the stack (orcheo install --start-stack).

macOS / LinuxWindows PowerShellSDKmacOS/Linux (non-interactive)Upgrade

bash <(curl -fsSL https://ai-colleagues.com/install.sh)

irm https://ai-colleagues.com/install.ps1 | iex

uv tool install -U orcheo-sdk
orcheo install

curl -fsSL https://ai-colleagues.com/install.sh | bash -s -- --yes --start-stack

orcheo install upgrade --yes

orcheo install syncs stack assets into ~/.orcheo/stack (or ORCHEO_STACK_DIR), updates .env with setup-selected values, and can start the stack with Docker Compose. Setup prompts for VITE_ORCHEO_CHATKIT_DOMAIN_KEY; you can skip and continue, but ChatKit UI features remain disabled until a valid key is configured.

The Agent Skill flow remains a strong option for workflow authoring with coding agents.

Subscription Required

Most AI coding agents (Claude Code, Codex CLI, Cursor) require a paid subscription. Free alternatives may exist but have not been tested with Orcheo.

1. Install the Orcheo Agent Skill¶

Add the Orcheo agent skill to your AI coding agent (Claude Code, Cursor, etc.) by following the installation instructions in the repo.

2. Let Your Agent Do the Work¶

Once installed, simply ask your agent to:

Set up Orcheo: "Set up Orcheo for local development"
Create workflows: "Create a workflow that monitors RSS feeds and sends Slack notifications"
Deploy workflows: "Deploy and schedule my workflow to run every hour"

Your AI agent will automatically:

Install dependencies
Start the backend server
Create and configure workflows
Handle authentication and deployment

That's it! Your agent handles the complexity while you focus on describing what you want your workflows to do.

Guides¶

Manual Setup Guide — Installation and configuration
Canvas — Workflow monitor, default-config editor, and Credential Vault manager
Auth0 IdP Setup — Configure Auth0 OAuth/OIDC for the Docker stack
MCP Integration — Connect AI assistants to Orcheo
Workflow Config Annotations — Declare typed configurable fields with a companion schema file
Conversational Search — Step-by-step demos from basic RAG to production-ready search
Evaluation — QReCC and MultiDoc2Dial benchmark workflows

Reference¶

CLI Reference — Command reference for the orcheo CLI
SDK Reference — Python SDK for programmatic workflow execution
Authentication Guide — Service tokens, OAuth, and JWT configuration
Environment Variables — Complete configuration reference

For Developers¶

Developer Guide — Repository layout, development environment, and testing
Deployment Guide — Docker Compose and PostgreSQL deployment recipes
Plugin Tutorial — Step-by-step guide: scaffold, register, test, and distribute a plugin
Plugin Reference — Full reference for all plugin authoring concepts and the registration API

Contributing¶

We welcome contributions from the community:

Share your extensions: Plugins, workflows, and integrations that extend Orcheo's capabilities. See the Plugin Tutorial to get started and the Plugin Reference for the full API.
How to contribute: Open an issue, submit a pull request, or start a discussion. You can also publish and share your extensions independently for others to install.