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.
Last verified:
What is Eddi?
EDDI is an open-source, enterprise-grade AI orchestration platform that enables teams to build, configure, and deploy AI-powered agents using JSON configuration rather than compiled code. It is a deployable middleware platform — not a library — providing a complete production-ready environment with a React management UI (EDDI Manager), built-in REST APIs, conversation state management, security (OIDC/Keycloak), immutable audit trails, and 42 MCP tools, all deployable via Docker or Kubernetes.
Key features include configuration-as-code (agent logic in JSON, no redeployment needed), 42 MCP tools for AI-native control via Model Context Protocol, security-first architecture with vault integration and cryptographic audit trails, enterprise-grade concurrency with millions of lightweight Java 25 virtual threads, multi-agent orchestration with intent-based discovery and A/B routing, built-in memory/context management, RAG with 7 embedding providers and 5 vector stores, model cascading to reduce LLM costs by 60-80%, scheduling with cron triggers and heartbeat wake-ups, and 12 ready-to-use agent tools including web search, calculator, PDF reader, weather, and HTTP calls.
EDDI is designed for enterprise teams who need a production-ready AI orchestration platform, prompt engineers who want to iterate without redeployment, regulated industries requiring audit trails and EU AI Act compliance, and platform teams building internal AI services for multiple departments. It supports 12 LLM providers including OpenAI, Anthropic Claude, Google Gemini, Mistral AI, Azure OpenAI, Amazon Bedrock, Ollama, and any OpenAI-compatible endpoint.
Eddi pricing
Pricing model: Freemium
EDDI is 100% free and open-source under the Apache 2.0 license. There is no paid tier, subscription, or enterprise pricing — the full platform including all features (EDDI Manager, 42 MCP tools, security, audit trails, RAG, model cascading, scheduling, and all 12 built-in agent tools) is available at no cost. The only costs users incur are their own LLM provider API keys (OpenAI, Anthropic, Google Gemini, etc.) and infrastructure costs for self-hosting (Docker, Kubernetes, MongoDB/PostgreSQL).
Eddi pros
- Open-source Apache 2.0 licensed — 100% free and enterprise-ready
- Configuration-as-code with JSON — no compiled code, instant iteration
- Production-ready React management UI (EDDI Manager) with 11 locales
- 42 MCP tools for AI-native control via Model Context Protocol
- Security-first: no eval(), AES-256-GCM vault, OIDC/Keycloak authentication
- Immutable HMAC-SHA256 cryptographic audit trails for compliance
- Enterprise concurrency: millions of Java 25 virtual threads for I/O-bound workloads
- Multi-agent orchestration with intent-based discovery and A/B routing
- Built-in RAG with 7 embedding providers and 5 vector stores
- Model cascading reduces LLM costs by 60-80%
- 12 ready-to-use agent tools: web search, calculator, PDF reader, weather, HTTP calls
- Persistent memory with dream consolidation and token-aware windowing
- Scheduling with cron triggers, heartbeat wake-ups, and dream cycles
- Deploy anywhere: Docker-native, Kubernetes/OpenShift-ready, air-gap support
- Supports 12 LLM providers including OpenAI, Anthropic, Google, Ollama
- 5,100+ tests with zero failures and zero Checkstyle warnings
- Red Hat Certified Container certified by IBM
- Import/export agents as ZIP with automatic secret scrubbing
- Live instance-to-instance sync with structural matching and content diffing
- Built-in Prometheus metrics and pre-built Grafana dashboards
Eddi cons
- Requires Docker or Java 25+ — not for lightweight serverless deployments
- Self-hosted only — no managed cloud SaaS offering available
- Steep learning curve for non-technical users despite visual UI
- MongoDB or PostgreSQL must be set up separately (not fully managed)
- API keys must be manually stored in Secrets Vault before creating agents
- Documentation is technical and geared toward developers, not beginners
- 18-year-old open-source project with chatbot roots may feel legacy to some
- No no-code visual workflow builder like Flowise or n8n drag-and-drop canvas
Frequently asked questions about Eddi
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 42 MCP tools — all deployable via Docker or Kubernetes.
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 via Docker.
Is EDDI production-ready for enterprise use?
Yes. EDDI is built on an enterprise-grade runtime with lightweight virtual threads for massive I/O-bound concurrency. It supports MongoDB and PostgreSQL, includes built-in OIDC/Keycloak authentication, provides immutable cryptographic audit trails for compliance (including EU AI Act), and scales horizontally via NATS JetStream.
What is the Model Context Protocol (MCP)?
The Model Context Protocol (MCP) is an open standard that allows AI assistants like Claude Desktop, IDE plugins, and custom clients to interact with external tools programmatically. EDDI exposes 42 MCP tools spanning conversation management, agent administration, setup automation, schedule management, and diagnostics.
Can EDDI replace Flowise or n8n for production workloads?
EDDI serves a similar visual-building purpose but with enterprise-grade architecture. Unlike Flowise and n8n, EDDI uses no eval() or code blocks, runs millions of lightweight virtual threads for enterprise-grade concurrency, supports OIDC/Keycloak authentication, and stores data in MongoDB or PostgreSQL. It is designed for regulated industries.
How do I store API keys securely?
Use the Secrets Vault. API keys and other sensitive values are encrypted at rest using envelope encryption (AES-256-GCM + PBKDF2). Via the Manager UI, navigate to Secrets in the sidebar and enter a key name and value — values are write-only and can never be retrieved through the API. In LangChain configs, reference secrets using vault syntax like ${eddivault:MY_API_KEY}.
How do I deploy to Kubernetes?
Use the one-command quickstart: kubectl apply -f https://raw.githubusercontent.com/labsai/EDDI/main/k8s/quickstart.yaml. For production, Kustomize overlays and Helm charts are available for MongoDB, PostgreSQL, auth, monitoring, and production hardening (HPA, PDB, NetworkPolicy).
What LLM providers does EDDI support?
EDDI supports 12 LLM providers across three categories: Cloud APIs (OpenAI, Anthropic Claude, Google Gemini, Mistral AI), Enterprise Cloud (Azure OpenAI, Amazon Bedrock, Oracle GenAI, Google Vertex AI), and Self-Hosted (Ollama, Jlama, Hugging Face). It also supports any OpenAI-compatible endpoint (DeepSeek, Cohere, etc.) via baseUrl configuration.
How do I create my first agent?
Use setup_agent to create a fully working agent in one call via MCP or REST API. Provide agentName, systemPrompt, provider (e.g., anthropic), model (e.g., claude-sonnet-4-6), and apiKey (referenced from EDDI vault). This creates the rules, LLM config, workflow, agent, and deploys it — all in one step.
What is the EDDI Manager?
The EDDI Manager is a comprehensive React-based management interface that provides visual control over every aspect of the EDDI platform — from agent configuration to real-time conversation monitoring. Key capabilities include visual agent builder, live chat debugging, audit dashboards for token usage and costs, 11-locale i18n with RTL support, interactive onboarding, resource management for rules/workflows/LLM configs/connectors, and Secrets Vault for secure API key management.