Core orchestration and workflow management for the clewcrew portfolio.
clewcrew-core provides the central workflow orchestration system that coordinates all expert agents, validators, and recovery engines to detect and resolve AI hallucinations in code.
# Install with pip
pip install clewcrew-core
# Install with UV
uv add clewcrew-corefrom clewcrew_core import ClewcrewOrchestrator
# Initialize the orchestrator
orchestrator = ClewcrewOrchestrator("/path/to/project")
# Detect hallucinations
hallucinations = await orchestrator.detect_hallucinations()
# Run complete workflow
final_state = await orchestrator.run_workflow()
# Recover from specific issues
recovery_results = await orchestrator.recover_from_issues(hallucinations)- ClewcrewOrchestrator: Main orchestrator class that manages the workflow
- ClewcrewState: State management for workflow execution
- LangGraph Integration: Built on LangGraph for robust workflow orchestration
- Detection: Expert agents detect hallucinations in code
- Validation: Validators confirm and prioritize findings
- Recovery Planning: System plans appropriate recovery actions
- Recovery Execution: Recovery engines fix identified issues
- Recovery Validation: System validates that fixes were successful
- Report Generation: Comprehensive report of the workflow execution
- clewcrew-common: Shared utilities and patterns
- clewcrew-framework: Base classes and abstractions
- langgraph: Workflow orchestration
- langchain: AI agent framework
- pydantic: Data validation and settings management
# Run tests
pytest tests/
# Run with coverage
pytest tests/ --cov=src/clewcrew_core --cov-report=htmlWe welcome contributions! Please see our Contributing Guide for details.
This project is licensed under the MIT License - see the LICENSE file for details.
Ready to orchestrate the clewcrew revolution! π§ β¨