EDDI
EDDI (Enhanced Dialog Driven Interface) is a Java/Quarkus multi-agent orchestration middleware for conversational AI. It routes conversations to one or more LLM providers, coordinates tool/API calls, and manages stateful, configurable conversation flows via a lifecycle pipeline and versioned JSON behavior rules. It can run as a Docker container (Kubernetes/OpenShift friendly) and includes built-in tools plus support for whitelisted HTTP-call tools.
Score Breakdown
⚙ Agent Friendliness
🔒 Security
README/docs mention security controls such as SSRF protection, sandboxed calculator evaluation, tool hardening, and a tool execution pipeline with rate limiting, caching, cost tracking/budget enforcement, and whitelisted HTTP-call tools. However, the provided content does not detail TLS enforcement requirements, secret handling/logging behavior, or fine-grained authorization scopes, so scores are conservative.
⚡ Reliability
Best When
You need a configurable middleware layer that manages agent routing, tool execution (including safe HTTP calls), and conversation state across multiple backend systems and LLMs.
Avoid When
You only need a lightweight chatbot UI or a single-model proxy with minimal security/tooling; the added orchestration/config complexity may be unnecessary.
Use Cases
- • Orchestrating multiple LLM providers based on conversation context/rules
- • Building stateful multi-step conversational experiences with tool/function calling
- • Integrating chat/agent flows with external REST APIs and business logic
- • Secure execution of tool calls with SSRF protection, rate limiting, caching, and budget enforcement
- • Deploying conversational middleware as a scalable, cloud-native service with metrics and health endpoints
Not For
- • Directly replacing an LLM API for simple single-call chat without orchestration needs
- • Uncontrolled agent tool execution where arbitrary outbound requests are acceptable (EDDI emphasizes whitelisting)
- • Environments that cannot run Java 21/Quarkus or require first-party managed SaaS
Interface
Authentication
Authentication is described as OAuth2 via Keycloak, but the README does not specify token flows, scopes, or authorization model details.
Pricing
No pricing information provided; project appears open-source and self-hosted via Docker/Kubernetes.
Agent Metadata
Known Gotchas
- ⚠ Tool execution is governed by configuration/rules; agents may fail to call tools if tool whitelisting/rate limits/budgets are not configured as expected.
- ⚠ Outbound web requests and SSRF-prone capabilities are protected; some URLs may be blocked due to SSRF protection rules.
- ⚠ HTTP-call tools rely on pre-configuration; agent behavior may be limited to allowed endpoints/parameters rather than free-form API calls.
Alternatives
Full Evaluation Report
Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for EDDI.
AI-powered analysis · PDF + markdown · Delivered within 30 minutes
Package Brief
Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.
Delivered within 10 minutes
Score Monitoring
Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.
Continuous monitoring
Scores are editorial opinions as of 2026-03-30.