3-Layer Brain architecture (STM, LTM, Galaxy Graph)Hybrid search (Keyword + Vector) using FastEmbedLocal-first memory server for AI agents60fps local dashboard for visualizing agent's brain

Not

Hacker

News!

AI-observed conversations & context

Daily AI-observed summaries, trends, and audience signals pulled from Hacker News so you can see the conversation before it hits your feed.

LiveBeta

Explore

Home
Hiring
Products
Companies
Discussion
Q&A

Tech Stack

PythonFastAPISQLiteD3.jsModel Context Protocol (MCP)

Artificial Intelligencememory localityKnowledge GraphsLarge Language Modelsllm

Discussion (1 comments)

Showing 1 comments

james_marks

20 days ago

I was ready to hate this, guessing it was a low-effort collection of text files.

But the approach looks very thoughtful.

I turned memory on for Claude, and quickly discovered that I didn’t want fragments of old conversations haunting new ones.

OP: how’s your day to day been using this? Do you find the memories are sometimes unwanted/off topic?

View on Hacker NewsHN ID: 46259498Mood: excited

Resources

Visit Hacker News
HN API
Modal cronjobs
Meta Llama

Briefings

Inbox recaps on the loudest debates & under-the-radar launches.

Connect

Not affiliated with Hacker News or Y Combinator. We simply enrich the public API with analytics.