Open-source memory for coding agents, synced over SSH • Hacker News Board

Re: Open-source memory for coding agents, synced over SSH

#41

Post by ubermon » Thu, Jul 16, 2026, 8:10 PM UTC

I think this is mostly being overengineered. At this stage, a curated MEMORY.md is enough: short, readable at session start, and easy to correct when it becomes stale.

The session history is another database like any other database, can be used or invoked by agent like one.

Re: Open-source memory for coding agents, synced over SSH

#42

Post by rayshan » Fri, Jul 17, 2026, 5:20 PM UTC

zby wrote: post #21

I did an automatic review of over 140 such systems. There are comparisons and stuff: https://zby.github.io/commonplace/agent-memory-systems/ Deja-vu is here: https://zby.github.io/commonplace/agent-memory-systems/revie... And the full list: https://zby.github.io/commonplace/agent-memory-systems/revie...

This is amazing work but frankly not very helpful for me as a user. What is your top 3 recommendation? I just want to install something that works.

Re: Open-source memory for coding agents, synced over SSH

#43

Post by stefan_iarca » Sun, Jul 26, 2026, 4:30 PM UTC

bityard wrote: post #14

esafak wrote: post #3

Similar to https://ctx.rs/ and others, I'm sure. I'd lead with your differentiation. Is it the ssh?

Maybe somebody can enlighten me... this page for ctx says the program saves all "decisions, constraints, intent, rejected approaches, bug investigations, refactors, file paths, commands, patches, and notes from previous agents." What am I missing if I instead just instruct the agent to create a handful of files called something like HISTORY.md and tell it to log summarized versions of all of these things inside the p…

[flagged]