Features
Provides MCP server interface for AI agents
Uses Joern Code Property Graphs for code representation
Supports querying function call chains and data flow
Enables natural language queries over code structure
Containerized for easy deployment and isolation
Integrates with LLMs and AI coding assistants
Supports multiple programming languages via Joern
Offers depth beyond simple code search
Facilitates automated code review and analysis
Enables debugging support through structural queries
Role-based agent assignment (PM, architect, engineer, QA)
Structured output generation (requirements, design, code)
Data Interpreter for data analysis tasks
SELA module for self-evolving agents
Multi-agent collaboration and workflow orchestration
Meta-programming support for custom agent behaviors
Modular and extensible architecture
Built-in demo projects and case studies
MIT License fully open-source
Flow orchestration for complex agent pipelines
Integration with GitHub Actions and CI/CD
Community-driven with GitHub and Discord
