$git clone https://github.com/labsai/EDDIE.D.D.I (Enhanced Dialog Driven Interface) is a production-grade, config-driven multi-agent orchestration middleware for conversational AI. It coordinates users, AI agents, and business systems through intelligent routing, persistent memory, and API orchestration — wi
| 1 |  |
| 2 | |
| 3 | # E.D.D.I — Multi-Agent Orchestration Middleware for Conversational AI |
| 4 | |
| 5 | [](https://www.bestpractices.dev/projects/12355) [](https://securityscorecards.dev/viewer/?uri=github.com/labsai/EDDI) [](https://app.codacy.com/organizations/gh/labsai/dashboard?utm_source=github.com&utm_medium=referral&utm_content=labsai/EDDI&utm_campaign=Badge_Grade) |
| 6 | |
| 7 | [](https://github.com/labsai/EDDI/actions/workflows/ci.yml) [](https://github.com/labsai/EDDI/actions/workflows/codeql.yml)   |
| 8 | |
| 9 | [](https://hub.docker.com/r/labsai/eddi) [](https://github.com/labsai/EDDI/releases) [](AGENTS.md) |
| 10 | |
| 11 | **E.D.D.I** (Enhanced Dialog Driven Interface) is a production-grade, **config-driven multi-agent orchestration middleware** for conversational AI. It coordinates users, AI agents, and business systems through **intelligent routing, persistent memory, and API orchestration** — without writing code. |
| 12 | |
| 13 | Built with **Java 25** and **Quarkus**. Ships as a **Red Hat-certified Docker image**. Selected as a **UNIDO Trusted Partner** for Industrial AI. Native support for **MCP** (Model Context Protocol), **A2A** (Agent-to-Agent), **Slack**, **OpenAPI**, and **OAuth 2.0**. |
| 14 | |
| 15 | [Website](https://eddi.labs.ai/) · [Documentation](https://docs.labs.ai/) · License: Apache 2.0 |
| 16 | |
| 17 | --- |
| 18 | |
| 19 | ## 📑 Table of Contents |
| 20 | |
| 21 | - [🏁 Quick Start](#-quick-start) |
| 22 | - [💡 Why EDDI?](#-why-eddi) |
| 23 | - [📸 See It In Action](#-see-it-in-action) |
| 24 | - [✨ Features](#-features) |
| 25 | - [📖 Documentation](#-documentation) |
| 26 | - [📋 Compliance & Privacy](#-compliance--privacy) |
| 27 | - [🏗️ Development](#️-development) |
| 28 | - [Prerequisites](#prerequisites) |
| 29 | - [Quarkus Dev Mode](#quarkus-dev-mode) |
| 30 | - [Maven Command Reference](#maven-command-reference) |
| 31 | - [Build & Docker](#build--docker) |
| 32 | - [Kubernetes](#️-kubernetes) |
| 33 | - [🤝 Contributing](#-contributing) |
| 34 | - [🔒 Security](#-security) |
| 35 | - [📜 Code of Conduct](#-code-of-conduct) |
| 36 | |
| 37 | --- |
| 38 | |
| 39 | ## 🏁 Quick Start |
| 40 | |
| 41 | The fastest way to get EDDI running is the **one-command installer**. It sets up EDDI + your choice of database via Docker Compose, deploys the [Agent Father](docs/agent-father-deep-dive.md) starter agent, and walks you through creating your first AI agent. |
| 42 | |
| 43 | **Linux / macOS / WSL2:** |
| 44 | |
| 45 | ```bash |
| 46 | curl -fsSL https://raw.githubusercontent.com/labsai/EDDI/main/install.sh | bash |
| 47 | ``` |
| 48 | |
| 49 | **Windows (PowerShell):** |
| 50 | |
| 51 | ```powershell |
| 52 | Invoke-WebRequest -UseBasicParsing -Uri "https://raw.githubusercontent.com/labsai/EDDI/main/install.ps1" -OutFile "install.ps1" |
| 53 | Unblock-File .\install.ps1 |
| 54 | .\install.ps1 |
| 55 | ``` |
| 56 | |
| 57 | Requires [Docker](https://docs.docker.com/get-docker/). The wizard auto-generates a unique vault encryption key for secret management. |
| 58 | |
| 59 | <details> |
| 60 | <summary><strong>🔧 Installer options</strong></summary> |
| 61 | |
| 62 | ```bash |
| 63 | bash install.sh --defaults # All defaults, no prompts |
| 64 | bash install.sh --db=postgres --with-auth # PostgreSQL + Keycloak |
| 65 | bash install.sh --full # Everything enabled (DB + auth + monitoring) |
| 66 | bash install.sh --local # Build Docker image from local source |
| 67 | ``` |
| 68 | |
| 69 | The `--local` flag is for contributors testing pre-release builds: |
| 70 | |
| 71 | ```bash |
| 72 | ./mvnw package -DskipTests # Build the Java app |
| 73 | bash install.sh - |