SynaLinks is an AI framework that combines deep learning with symbolic reasoning using JSON-based data flows and knowledge graphs. In this community call, PhD researcher and a CEO of SynaLinks, Yoan Sallami will present how SynaLinks reimagines Keras to support dynamic, self-organizing agents and integrates seamlessly with Memgraph for real-time retrieval, schema-aware extraction, and secure LLM interactions.

This session will include a demo, architectural insights and a look at how teams can build advanced AI systems using open graph tools. Join us to explore how SynaLinks is pushing the boundaries of graph-powered AI.

Dr Yoan Sallami is a PhD in HRI (human-robot interactions), specialized in neuro-symbolic architectures, he is the author of Synalinks, a fork of Keras designed for neuro-symbolic Language Models applications. Synalinks aims at bridging the gap between neural networks and symbolic reasoning to create systems that businesses can rely upon.

From Tensors to Triplets: Redefining Deep Learning with Knowledge Graph Based Agents