labsai/EDDI

Multi-agent orchestration middleware that coordinates between users, AI agents (LLMs), and business systems. It provides intelligent routing, conversation management, and API orchestration for building sophisticated AI-powered applications.

63
/ 100
Established

Built on Java/Quarkus with a **Lifecycle Pipeline architecture**, EDDI processes conversations through configurable, composable stages (parsing → rules → API/LLM invocation → output) rather than direct forwarding to LLMs. It includes autonomous AI agent tooling (calculator, web search, weather, PDF reader) with built-in security controls—SSRF protection, sandboxed evaluation, rate limiting, and cost tracking—plus the ability to expose custom HTTP APIs as whitelisted tools for agents. Integrates with OpenAI, Claude, Gemini, Ollama via langchain4j, stores bot configs and conversation history in MongoDB, and runs as a certified Docker image on Kubernetes/OpenShift.

289 stars.

No Package No Dependents
Maintenance 13 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 24 / 25

How are scores calculated?

Stars

289

Forks

102

Language

Java

License

Apache-2.0

Last pushed

Mar 28, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/labsai/EDDI"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.