How we taught a Java AI assistant to find memories by meaning, not just keywords using Spring AI, Ollama, and pgvector.
How we taught a Java AI assistant to find memories by meaning, not just keywords.
Where We Left Off
In Part 2, I explained the architecture behind Jarvis AI Platform's memory system.
We had four layers planned:
Working Memory ✅ (Phase 1)
Most "agent memory" today is one thing wearing three hats: a vector database.You embed the past, you...
Vector similarity finds what looks like your question. It cannot explain why a decision was made six months ago. velesdb-memory…
AI Memory Systems: Transforming How Large Language Models Understand You ...
By Nidhi: Built for the Global AI Hackathon Series with Qwen Cloud, Track 1: MemoryAgent When I...
How I Gave My AI Coding Agent Persistent Memory in 2 Minutes Every AI coding session...
Most AI chatbots are stateless. They forget everything once the conversation ends. But modern AI...
