Open-source Java/SpringAI/Spring Boot AI enablement/orchestration layer for applications with RAG, governed actions, providers, vector stores, PII, tenant safety, chat memory, and behavior analysis.
https://ai-fabric.dev β// readme
Build conversations, event-driven intelligence and bounded specialist teams around your existing
data and services. Your application keeps control of identity, policy, business state and execution.
Β· Β·
The Idea
Your application already knows who the user is, what they may access, which records are current, and how a business operation should execute. AI should use those capabilities, not replace them.
AI Fabric adds a modular intelligence layer: understand a request, retrieve authorized evidence, consult live services, coordinate specialists, and propose or execute permitted application actions. Use it behind a chat interface, call it from Java, or invoke it from an application-owned event handler.
The model interprets, reasons and proposes. Your application owns authority and side effects.
Built on Spring AI for model integration and document ETL, with opinionated contracts for application data, governed execution, specialist composition and human participation. Install only what you need; neither a vector database nor a chat interface is required for every use case.
Four Ways To Build
1. Conversations That Use Your Application
**βCompare theseβ¦