{"id":"labsai-eddi","name":"EDDI","homepage":"https://eddi.labs.ai","repo_url":"https://github.com/labsai/EDDI","category":"ai-ml","subcategories":[],"tags":["ai","multi-agent","orchestration","conversation-memory","conversational-ui","java","quarkus","mcp-client","mcp-server","mongodb","postgres","prompt-management","restful-api","kubernetes","security"],"what_it_does":"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.","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"],"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.","alternatives":["LangChain/LangGraph-style orchestration libraries","Microsoft Semantic Kernel","Self-hosted agent frameworks using your own orchestration (e.g., custom middleware + tool calling)","Other multi-agent orchestration middleware solutions (vendor-specific or open-source equivalents)"],"af_score":61.8,"security_score":55.5,"reliability_score":38.8,"package_type":"mcp_server","discovery_source":["github"],"priority":"high","status":"evaluated","version_evaluated":null,"last_evaluated":"2026-03-30T13:34:07.845999+00:00","interface":{"has_rest_api":true,"has_graphql":false,"has_grpc":false,"has_mcp_server":false,"mcp_server_url":null,"has_sdk":false,"sdk_languages":["Java"],"openapi_spec_url":null,"webhooks":false},"auth":{"methods":["OAuth 2.0 (Keycloak) for authentication and user management (as stated)"],"oauth":true,"scopes":false,"notes":"Authentication is described as OAuth2 via Keycloak, but the README does not specify token flows, scopes, or authorization model details."},"pricing":{"model":null,"free_tier_exists":false,"free_tier_limits":null,"paid_tiers":[],"requires_credit_card":false,"estimated_workload_costs":null,"notes":"No pricing information provided; project appears open-source and self-hosted via Docker/Kubernetes."},"requirements":{"requires_signup":false,"requires_credit_card":false,"domain_verification":false,"data_residency":[],"compliance":[],"min_contract":null},"agent_readiness":{"af_score":61.8,"security_score":55.5,"reliability_score":38.8,"mcp_server_quality":0.0,"documentation_accuracy":75.0,"error_message_quality":0.0,"error_message_notes":null,"auth_complexity":70.0,"rate_limit_clarity":80.0,"tls_enforcement":70.0,"auth_strength":75.0,"scope_granularity":35.0,"dependency_hygiene":45.0,"secret_handling":45.0,"security_notes":"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.","uptime_documented":20.0,"version_stability":60.0,"breaking_changes_history":40.0,"error_recovery":35.0,"idempotency_support":"false","idempotency_notes":null,"pagination_style":"none","retry_guidance_documented":false,"known_agent_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."]}}