CrewAI Agent Deployment Orchestrator
Cross-platform deployment orchestration for CrewAI agents. Analyze agent codebases and generate optimized Docker configurations with one command.
Quick Start
# Install
pip install crewai-deploy-orchestrator
# Analyze an agent and generate deployment configs
crewai-deploy /path/to/agent --output ./deployment
# Or use directly with Python
python -m orchestrator /path/to/agent --output ./deployment
Installation
From PyPI
pip install crewai-deploy-orchestrator
From Source
git clone https://github.com/yourorg/crewai-deploy-orchestrator.git
cd crewai-deploy-orchestrator
pip install -r requirements.txt
Development Installation
pip install -e ".[dev]"
Features
- Agent Analysis: Parse CrewAI agent definitions to extract dependencies
- Dependency Detection: Identify Python packages and system requirements
- Docker Generation: Create optimized Dockerfile and docker-compose.yml
- Health Monitoring: Built-in health checks and monitoring setup
- Multi-Platform: Ready for cloud deployment (AWS, GCP, Azure, etc.)
Usage Examples
Basic Usage
# Analyze an agent and generate deployment configs
crewai-deploy /path/to/agent --output ./deployment
# With custom agent name
crewai-deploy /path/to/agent --output ./deployment --agent-name my-agent
Example with Included Examples
# Test with included examples
crewai-deploy examples/simple_agent --output simple_deployment
# Deploy
cd simple_deployment
docker-compose up -d
Output Structure
The tool generates the following files:
deployment/
├── Dockerfile # Optimized container definition
├── docker-compose.yml # Multi-service orchestration
├── requirements.txt # Python dependencies
├── health_check.py # Health monitoring endpoint
├── prometheus.yml # Monitoring configuration
└── logs/ # Log directory (mounted volume)
How It Works
1. Agent Analysis
The tool scans your CrewAI agent codebase for:
- Python imports and dependencies
- Agent class definitions (Agent, CrewAI patterns)
- Requirements files (requirements.txt, setup.py, pyproject.toml)
- System package requirements (apt-get install patterns)
2. Dependency Resolution
- Extracts all Python package dependencies
- Identifies system-level requirements
- Creates optimized installation order
3. Docker Configuration
- Generates optimized Dockerfile with caching
- Creates docker-compose.yml with health checks
- Includes monitoring setup (Prometheus)
- Sets up volume mounts for persistence
4. Health Monitoring
- Built-in FastAPI health endpoint
- Resource usage monitoring (CPU, memory)
- Agent status reporting
- Ready for integration with monitoring stacks
Testing
Run the test suite:
python test_orchestrator.py
The test suite includes:
- Simple agent analysis
- Web research agent analysis
- CLI interface testing
- Docker config generation
Example Agents
The repository includes two example agents:
1. Simple Agent (examples/simple_agent/)
- Basic data analysis agent
- Report generation workflow
- Minimal dependencies
2. Web Research Agent (examples/web_research_agent/)
- Multi-agent research system
- Web scraping capabilities
- Async processing
- Comprehensive reporting
Deployment Options
Local Development
docker-compose up -d
Production Considerations
- Set environment variables for API keys
- Configure resource limits in docker-compose.yml
- Add SSL/TLS termination
- Set up proper logging and monitoring
- Implement backup strategies
Cloud Deployment
- AWS: Deploy to ECS/EKS with Load Balancer
- GCP: Deploy to Cloud Run or GKE
- Azure: Deploy to Container Apps or AKS
- Kubernetes: Use generated manifests with
kompose convert
Configuration
Environment Variables
# Agent configuration
OPENAI_API_KEY=your_key_here
LOG_LEVEL=INFO
PYTHONPATH=/app
# Docker configuration
MEMORY_LIMIT=2g
CPU_LIMIT=1.0
Customizing Deployment
Edit generated files:
Dockerfile: Add custom build stepsdocker-compose.yml: Adjust resource limits, add servicesprometheus.yml: Configure monitoring targetshealth_check.py: Add custom health checks
Limitations (MVP)
- Currently supports Python/CrewAI agents only
- Basic dependency resolution (no conflict handling)
- Assumes FastAPI for health endpoints
- Limited system package detection
- No automatic cloud deployment integration
Roadmap
- Advanced dependency conflict resolution
- Cloud provider templates (AWS, GCP, Azure)
- Kubernetes manifests generation
- Database and cache integration
- Secret management
- CI/CD pipeline templates
- Multi-language agent support
- Performance optimization recommendations
Contributing
- Fork the repository
- Create a feature branch
- Add tests for new functionality
- Submit a pull request
License
MIT License - See LICENSE file for details.
Community
- GitHub Issues: Report bugs and feature requests
- Discussions: Share ideas and ask questions
- CrewAI Discord: Join the CrewAI community
Built for the CrewAI ecosystem • Deploy agents anywhere with confidence
Metadata
Release files for crewai-deploy-orchestrator 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| crewai_deploy_orchestrator-0.1.0.tar.gz | 5.1 kB | Without provenance | Details for crewai_deploy_orchestrator-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| crewai_deploy_orchestrator-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for crewai_deploy_orchestrator-0.1.0-py3-none-any.whl |
Total release size: 10.1 kB
Release files / crewai_deploy_orchestrator-0.1.0.tar.gz
| Download URL | crewai_deploy_orchestrator-0.1.0.tar.gz |
|---|---|
| Size | 5.1 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
e7564d5457447abe9179c7908ccba2dcda8efcd10785ae11c9c26ae10bf974d9
|
|
BLAKE2b-256 checksum How to use checksums |
29a52e466df634af36ea1d7c13fe0ded4ef0dbde6206e2e2af54fbaf1115ce3a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.13
|
Release files / crewai_deploy_orchestrator-0.1.0-py3-none-any.whl
| Download URL | crewai_deploy_orchestrator-0.1.0-py3-none-any.whl |
|---|---|
| Size | 5.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
971188da835984b28cd01a40a18632010d9cbb2a9bbb4f397d6e480286b2e395
|
|
BLAKE2b-256 checksum How to use checksums |
e668b614715091bb37879f80fc17938f4665666128e8d6aee4c22a5f28355587
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.13
|
Security for crewai-deploy-orchestrator 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.