[!WARNING] ✨ Alpha Release is Here! This project is currently in alpha. Please use with caution, as it may contain bugs and undergo significant changes.

Next-level Agentic Orchestration Platform

Compozy orchestrates multi-agent AI systems with ease. Compozy's enterprise-grade platform uses declarative YAML to deliver scalable, reliable, and cost-efficient distributed workflows, simplifying complex fan-outs, debugging, and monitoring for production-ready automation.

✨ Key Features

• Declarative Workflows: Define complex AI workflows with simple, human-readable YAML.
• Developer-Focused: A comprehensive CLI with hot-reloading for a seamless development experience.
• Advanced Task Orchestration: 8 powerful task types including parallel, sequential, and conditional execution.
• Extensible Tools: Write custom tools in TypeScript/JavaScript to extend agent capabilities.
• Multi-Model Support: Integrates with 8+ LLM providers like OpenAI, Anthropic, Google, Cerebras, and local models.
• Enterprise-Ready: With Temporal behind the scenes, Compozy is built for production with persistence, monitoring, and security features.
• High Performance: Built with Go at its core, Compozy delivers exceptional speed and efficiency.

🚀 Getting Started

Get up and running with Compozy in just a few minutes.

Install via Homebrew (macOS/Linux)

brew tap compozy/homebrew-compozy
brew install compozy

Install via NPM

npm install -g @compozy/cli
# Or with Yarn
yarn global add @compozy/cli
# Or with pnpm
pnpm add -g @compozy/cli

Quick Start

# Create a new project
compozy init my-ai-app
cd my-ai-app

# Start the development server
compozy dev

Note: When using MCP tools in standalone mode, ensure mcp_proxy.port is set to a fixed port (not 0). See MCP Configuration for details.

For a complete walkthrough, check out our Quick Start Guide.

📚 Documentation

Our documentation website is the best place to find comprehensive information, tutorials, and API references.

| Section | Description | | ----------------------------------------------------------------------------------- | ------------------------------------------------ | | 🚀 Getting Started | Installation, setup, and your first workflow | | 🛠️ Configuration | Project, runtime, and provider configuration | | 🎨 Template Engine | Dynamic YAML configuration with templating | | 🤖 Agents | Building and configuring AI agents | | ⚙️ Tasks | Orchestrating operations with various task types | | 🔧 Tools | Extending agent capabilities with custom tools | | 🧠 Memory & Context | Managing agent memory and conversation context | | 🔌 MCP Integration | Model Context Protocol for external tool servers | | 📡 Signal System | Event-driven communication between components | | 🚀 Deployment | Deploy Compozy to production environments | | 💻 CLI Reference | Command-line interface reference | | 📋 Schema Definition | YAML schema definitions for all components | | 🔌 API Reference | REST API for programmatic access |

➡️ Explore the full documentation

🤝 Community & Contributing

We welcome contributions from the community! Whether it's reporting a bug, suggesting a feature, or submitting a pull request, your input is valuable.

• GitHub Issues: Report bugs and request features.
• Contributing Guide: Learn how to contribute to the project.

🔐 License

This project is licensed under the Business Source License 1.1 (BUSL-1.1). See the LICENSE file for details.