Hacker News new | ask | show | jobs
user: JosephjackJR
created: 2025-12-02
karma: 11

Hardware guy!

submissions:

0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
Show HN: Local memory layer for AI agents, survives restarts, no embeddings
2 points | 0 comments
0 points | 0 comments
0 points | 0 comments
Agent memory is structured not fuzzy.why are we all using vector DBs for it?
2 points | 3 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
Two orders of magnitude faster Persistent AI memory via a binary lattice
1 points | 2 comments
Show HN: Synrix local-first memory engine (O(k) retrieval, no vectors, no cloud)
2 points | 0 comments
0 points | 0 comments
0 points | 0 comments
Cloud costs are the #2 expense at midsize IT companies. Is this sustainable?
1 points | 3 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
The $1M Annual Cost of RAM-Bound Vector Databases in the Cloud
2 points | 2 comments
Show HN: Synrix – A Zero-Loss, Sub-Microsecond Memory Engine for Edge Compute
3 points | 0 comments
0 points | 0 comments
Fuck RAM Limits 50M Persistent Nodes on a $199 Jetson (186 ns, CPU-only)
4 points | 1 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
Why real-time AI memory is still slow, and a different approach
2 points | 5 comments