8 Comments
User's avatar
Michael Housman's avatar

Great piece! A lot of people don't realize how multi-faceted Claude is!

Claire Morrison's avatar

Totally! It's almost like an app that can build itself -- if the feature you want doesn't exist in Claude already (like a robust memory system), you can figure out how to create it with Claude Code.

Odin's Eye's avatar

Thank you. Great work Claude—and mentors

Gabe Weiss's avatar

You realize and learn to do these things when you get frustrated with LLMs forgetting everything.

Pawel Jozefiak's avatar

This local-first memory approach is exactly what I landed on after the Limitless EU ban hit.

After losing access to 6 months of voice data overnight, I built a similar setup: Claude reads a structured markdown context file at each session start. The difference from Limitless: the files are mine, portable, no vendor risk, no privacy theater.

The 'Claude updates notes automatically' framing undersells the harder problem though. Of 10GB of voice data I had, maybe 10% was genuinely useful context. Signal-to-noise is the real design challenge.

Full Limitless experience: https://thoughts.jock.pl/p/limitless-pendant-eu-ban-what-i-did-with-voice-data

Parvathy Krishna's avatar

This is great! Super helpful!

Claire Morrison's avatar

You're going to need to write a co-authored post with us soon, you're crushing the agent automations!

Parvathy Krishna's avatar

You're light-years ahead! I'm just trying to keep up.