Memoria – A Self‑Evolving Personal AI with Human‑like Memory

A developer built Memoria, a personal AI with human-like memory that remembers, forgets, and evolves by extracting personal facts, resolving contradictions, and reflecting on knowledge. The system was developed for the Qwen Cloud Hackathon and deployed on Alibaba Cloud using a three-tier memory architecture with hybrid scoring, decay, and conflict resolution. Memoria integrates with Qwen agents via a MemoryAgent API and is available as an open-source project.

Most AI assistants forget everything after each session. Memoria remembers, forgets, and evolves—extracting personal facts, resolving contradictions, and reflecting on what it knows. This post shares the journey of building a production‑ready MemoryAgent for the Qwen Cloud Hackathon, Track 1 . Every conversation with a typical chatbot starts from zero. You tell it you're allergic to peanuts on Monday, and by Wednesday it recommends pad thai with crushed peanuts. The model doesn't forget; it never had long‑term memory in the first place. Without durable knowledge about who you are, real personalisation is impossible. We built Memoria to solve that problem: a personal AI with human‑like memory that remembers what matters, forgets what fades, resolves contradictions, and evolves its understanding of you over time. Real memory isn't a bigger context window—it's extraction, prioritisation, decay, consolidation, and reflection. The hackathon challenged us to deliver a memory‑efficient, production‑grade MemoryAgent, and we built one from the ground up on Alibaba Cloud. Memoria organises knowledge in three deliberate tiers: text-embedding-v3 , ranked by hybrid scoring, and subject to decay, consolidation, and conflict resolution.Other key features: get core memories , get user preferences , forget memory , and strengthen memory to any Qwen agent. Backend : Python FastAPI, SQLAlchemy async, PostgreSQL 16 + pgvector for hybrid vector search. Memory pipeline : DashScope – Qwen‑Plus for chat/extraction/conflict/reflection, Qwen‑Max for consolidation, text-embedding-v3 for embeddings. Background workers : Celery handles memory ingestion, decay, and consolidation with Redis as the broker. Frontend : React + Vite, react-markdown , remark‑math , rehype‑katex , custom dark theme. Deployment : Docker Compose, Terraform for Alibaba Cloud ECS, ApsaraDB, Redis , Let's Encrypt via Nginx. qwen3-plus not accessible; standardised on qwen-plus .Voice input, multi‑agent collaboration via MCP, a mobile companion, advanced memory visualisations, and fine‑tuning Qwen on memory tasks. Try it yourself: https://memoria.imawais.engineer https://memoria.imawais.engineer GitHub: imawais-engineer/Memoria https://github.com/imawais-engineer/Memoria Built with ❤️ on Alibaba Cloud and Qwen Cloud .