I’ve been working on Mati, a personal AI that runs entirely locally with encrypted memory. My goal was to model memory as a continuous process (a phase field) rather than a static database. I wanted to share the architecture and the honest limitations. For example, in my tests, field-based retrieval scored 0.036, while lexical retrieval scored 0.838. I document all of this, including the negative results, in the ARCHITECTURE.md. It’s built for CPUs, respects privacy by design, and is Apache-2.0. I’d love feedback from this community.(https://github.com/vml520/Mati)
AI & ML
Mati: personal AI
dev.to Python0 views
Source:https://dev.to/serial-theorist/mati-personal-ai-4a1
PreviousHow wide are London's pavements? Measuring 7,908 cross-sections in WhitechapelNextSingle agent or multi-agent? What I learned building a multi-agent financial intelligence system
Related posts
Google is making it easier to opt out of Gemini AI model training – here’s how
0ZDNet
I’ve Used VSCO’s Lightroom Rival Desktop Editor and It’s Great for Creatives
0CNET News

Replit’s agent swarms built an app monitoring platform in 2 days on a $3K budget. Now, it’s offering them to customers.
0The New Stack
Dunkelflaute: Why cloudy, windless weather is a challenge for power networks that rely on renewables
0Phys.org Tech
What AI regulation could learn from the most hazardous industries in the world
0Phys.org Tech
Solar-powered radiation detector for use in disaster zones
0Phys.org Tech