Memmy Agent - Let every AI remember the same you.

@kelly_king3 Same here — memory was always the part that broke first in our agent experiments. Curious to hear how Memmy holds up in your setup.

@kelly_king3 Thanks Kelly! Yeah, once the flow gets agentic, memory is usually the first thing to fall over. Hope Memmy helps close that gap for you 🙌

@kelly_king3 Same pain. Agentic flows need memory that sticks across steps, not just the last chat turn. Excited for you to try it — tell us where it still feels thin once you’re in!

Thank you! That gap between individual agent runs and durable, usable context across a workflow is exactly what we’re trying to close. We’d love to hear what breaks—or works especially well—in your own agentic experiments once you’ve had a chance to try it.

@sabber_ahamed Yep, that’s the real tradeoff. There’s no automatic cloud sync today, so a brand-new machine won’t magically have your memory.

The memory pool is a local SQLite database, though, and you can export it and move it over. So a laptop swap only resets you if you leave the local store behind.

Right now it’s portable, but not seamlessly synced — the user controls the move.

@sabber_ahamed Exactly this tradeoff. Curious — for you, is “I move the DB myself” fine for now, or is seamless sync a must-have before you’d trust it day to day?

@sabber_ahamed Yeah, that’s the real fork. For now we bias local control + manual export/import; whether seamless sync should come next is exactly the feedback we want 🙌

That’s exactly the tradeoff. Local-first is great for privacy and control, but continuity cannot depend on one laptop forever.

The ideal model is user-controlled portability: encrypted export/import or an end-to-end encrypted sync option, where the user—not the platform—controls the memory pool and its keys. A new machine should be able to restore continuity without turning “local-first” into “we silently keep your memory in the cloud.”

Otherwise, a hardware refresh becomes an accidental memory wipe, which is too high a price for privacy.

@jody_l_wyatt That’s a great use case — and yes, team onboarding is already on our roadmap. So much of the real “how we actually work” never makes it into official docs; we’d love Memmy to help capture that tribal knowledge and make it usable for new hires. Appreciate you calling this out!

@jody_l_wyatt Love this — official docs never capture how work actually gets done. Memmy’s a natural fit for that tribal knowledge during onboarding 🙌

@arthurdls Exactly. The real win is not having to re-enter the same little preferences every time. Memmy can carry those across agents; the actual booking flow still depends on the tools you connect.

Curious which one you’d test first — flights or shopping?

@arthurdls +1 — love this use case. Things like preferred airlines, aisle vs window, budget range, clothing sizes/brands… once those stick in memory, every new agent starts much closer to “you.” Would be fun to see which preference set you teach it first ✈️🛍️

@arthurdls Love this use case — once preferences stick, shopping/flights get so much less annoying. Memory can follow you across agents; booking still depends on the tools you wire in 🙌

@victor_paraschiv Then you’re exactly the person we’d love feedback from 😄 Would really appreciate an upvote, and give Memmy a spin when you can — curious how it feels coming from claude_mem.

@victor_paraschiv Love that you’ve already been deep in this problem with claude_mem 🙌 Would love to hear how it feels once you try it! ✨

@victor_paraschiv Thanks Victor! If you’ve been living in claude_mem, you might like that Memmy also works across Claude Code / Cursor / Codex — same memory, not just one tool 🙌

@1251912798 Glad that stood out. ✌️ The boring security details matter a lot once an agent starts touching real work. We’re trying to make the safer path the default, not something you have to remember to fix later.

@1251912798 +1 — Pema said it perfectly. Love that this detail stood out to you 🙌

@1251912798 Thanks! Secure defaults should feel boring in the best way — less “remember to harden it later,” more safe out of the box 🔐

@1251912798 Secure defaults should make the safe path the easiest path. Keeping API keys out of configuration files reduces the risk of accidental exposure and makes credentials easier to manage across environments. We’re working to support environment-variable references as soon as possible.

@thea5 Exactly 😅 Getting an AI to learn your voice shouldn’t be something you have to redo in every new chat.

、

@thea5 Love this use case — writing voice is such a pain to re-teach every time. Would be great if yours just followed you across tools ✨

@thea5 Haha the timing is always perfect… right before a new chat wipes it 😅 Would love Memmy to make your writing voice the thing that actually sticks. Which tool do you write in most?

@wys1010 Totally agree👍 That kind of retrieval analytics is a big unlock for both trust and quality. We already expose some of this in Memory Logs (candidates, what got filtered / dropped, what was actually injected), and we’re keen to push further toward clearer “helped / ignored / corrected” signals so users can steer the system and we can keep improving recall. Great call.

@wys1010 Thanks! Totally with you — being able to see how memories get used (or skipped) is a big part of making the system feel trustworthy 👍

Retrieval analytics could make memory much more observable and trustworthy.

Showing which memories were used, ignored, contradicted, or later corrected would give users a clear way to audit what influenced an answer. It would also help the system identify stale, low-value, or conflict-prone memories and improve retrieval over time.

The key is to present it as an understandable “memory trace,” with privacy-preserving local analytics by default—not an opaque scoring system.

@nicole_h94 Yes!! You totally get it 🙌 Storage is easy — the real magic is surfacing the right decision to the agent working on today’s task. That’s exactly what Memmy is built for. Love this take 💚

@nicole_h94 Spot on — saving notes is easy; the hard part is surfacing the right one while the agent is actually doing today’s work ✨

@tristan_huang Thanks so much! That was exactly our goal — make the privacy story concrete, not just a slogan. Local SQLite + you control the access 🔐

@tristan_huang Thanks Tristan! Glad the local-first details landed — we wanted people to actually see where the data lives, not just trust a vague “privacy-first” line 🙌