The Enterprise AI Orchestrator | EDDI Skip to content 🏆 UN Recognition LABS.AI selected as UNIDO Trusted Partner for Industrial AI Read more →
Get Started EN English EN Deutsch DE Español ES Français FR Português PT العربية AR 中文 ZH 日本語 JA 한국어 KO हिन्दी HI ไทย TH
Features<br>✨ All Features 🖥️ EDDI Manager 🔌 MCP Server (65 Tools) ⚙️ Config-as-Code 🔐 Security-First 🚀 Performance 🤖 Multi-Agent 📊 Observability 🧪 Code Quality 🧩 AI-Ready 🧠 Memory & Context 📚 RAG 📈 Model Cascading ⏰ Scheduling<br>Solutions<br>💡 Why EDDI? ⚖️ vs. Alternatives 🏛️ Compliance 📜 Track Record 📋 Use Cases<br>Resources<br>📖 Documentation ↗ 🐙 GitHub ↗<br>Get Started<br>Switch to Light Mode Switch to Dark Mode
The Enterprise AI Orchestrator<br>The open-source, production-ready platform for deploying governed, multi-agent AI systems. Configuration-driven, self-hosted, and compliance-ready — with a visual management UI, 65 MCP tools, and enterprise security built in. Now in v6 (latest: 6.1.2).<br>Get Started → View on GitHub ↗ Demo System
The Problem<br>Enterprise AI orchestration is fragmented and painful . Teams are stuck in a broken lifecycle:
The Prototype Trap<br>Teams prototype with Flowise, n8n, or scripts — then rewrite everything from scratch for production. Visual prototypes are discarded entirely.
Boilerplate Fatigue<br>Using AI libraries means building REST controllers, auth layers, and state management from scratch . Every prompt tweak requires redeployment.
BPMN Friction<br>Forcing non-deterministic AI agents into deterministic Camunda/Temporal workflows creates severe impedance mismatches and brittle architectures.
The Solution<br>EDDI is a deployable AI orchestration platform — not a library. Visual management, config-as-code, and enterprise security, out of the box:
01<br>Configuration-as-Code<br>Agent logic, pipelines, and tool definitions are JSON configurations — not compiled code. Prompt engineers iterate instantly via the React UI or REST API, without redeployment.
02<br>65 MCP Tools<br>EDDI exposes its capabilities via the Model Context Protocol — enabling Claude Desktop to interact. Agents can also consume external MCP tools .
03<br>Security-First<br>No eval(), no escapes. Vault integration, URL validation, and cryptographic audit trails are architectural foundations .
04<br>Observability<br>Every pipeline step is logged with an immutable audit trail — tokens, cost, timing, tool calls. Full CQRS telemetry ledger.
05<br>Enterprise Concurrency<br>Built on an enterprise-grade runtime with millions of lightweight threads for I/O-bound LLM workloads. No event loop blocking, no single-threaded bottlenecks.
06<br>Multi-Agent Orchestration<br>Intent-based agent discovery, managed conversations, agent triggers, and A/B routing. One conversation per intent+user , auto-created and auto-managed.
"The engine is strict so the AI can be creative."
— Project Philosophy<br>United Nations Recognition<br>UNIDO Trusted Partner for Industrial AI<br>LABS.AI has been selected by the United Nations Industrial Development Organization (UNIDO) as a Trusted Partner for Industrial AI for the Global South.<br>Learn more about the partnership →
Trusted & Certified
Red Hat Certified Container Docker image certified by IBM
Apache 2.0 Licensed 100% open-source & enterprise-ready
9,600+ Tests · 0 Failures Rigorous CI/CD & >90% code coverage
OpenSSF Gold Highest tier of Linux Foundation security & quality certification
Docker Hub Container pulls from Docker Hub
CI Passing · CodeQL Clean Automated builds, security scanning & code analysis
Built on Proven Technology
Java 25 Enterprise runtime<br>Quarkus Cloud-native, fast<br>LangChain4j Multi-provider LLM support<br>MongoDB Document store<br>PostgreSQL Relational store<br>Docker Container-ready<br>Kubernetes Orchestration<br>OpenShift Red Hat certified
Next Steps
Get Started in 5 Minutes Install EDDI, create your first agent, and start a conversation. Explore All Features Config-as-Code, MCP tools, security, observability, and more. Why EDDI? Learn why configuration-driven AI orchestration beats code-first approaches. Browse Documentation ↗ Architecture, MCP tools, REST API, deployment guides, and more.
Frequently Asked Questions
What is EDDI? EDDI is an open-source, enterprise-grade AI orchestration platform. It enables teams to build, configure, and deploy AI-powered agents using JSON configuration rather than compiled code. EDDI provides a complete platform with a production-ready React management UI (the EDDI Manager), built-in REST APIs, conversation state management, security (OIDC/Keycloak), immutable audit trails, and 65 MCP tools — all deployable via Docker or Kubernetes.<br>How is EDDI different from AI libraries and frameworks? AI libraries like LangChain, Spring AI, and LangChain4j give you building blocks — but you still need to build REST controllers, authentication, conversation state management, audit logging, and management UIs yourself. EDDI is a deployable middleware platform , not a library. It provides all of this out of the box, ready to deploy...