EDDI
Config-driven engine that turns JSON into production-grade AI agents. Multi-agent orchestration, 12+ LLM providers, MCP/A2A protocols, RAG, persistent memory, and enterprise compliance (EU AI Act, GDPR, HIPAA). Built on Quarkus.
EDDI is a production-grade, config-driven multi-agent orchestration middleware built with Java 25 and Quarkus. It coordinates users, AI agents, and business systems through intelligent routing, persistent memory, and API orchestration without writing code. It offers enterprise security, compliance, and observability, supporting multiple LLM providers and standard protocols with one-command Docker deployment.
Features
Compatibility
Quick start
Use cases
Alternatives
Related searches
Comments
- EElliot NguyenMay 5, 2026
JSON-driven config for production-grade agents reduces code surface area considerably.
- OOakley PatelApr 27, 2026
Multi-agent coordination built into the engine, not bolted on.
- Kendall RiveraMar 30, 2026
Good for teams who want agent behavior defined in config, not code.
- JJamie HarrisMar 10, 2026
Config-driven approach makes agent definitions reviewable and version-controllable.
- CCameron DavisFeb 27, 2026
Production-ready from the start, not a prototype framework.