Every cold conversation is a missed deal, delayed project, or broken trust. Shram listens across your Mac - Gmail, Slack, WhatsApp, GMeet, etc - and resolves them before they slip. One click. No integrations.
This is the 3rd launch from Shram. View more
Minimi
Launching today
Every great Claude response starts with context. Minimi listens across your Mac - docs, calls, messages, tabs - and gives Claude the full picture. No prompting. All on-device and private.
Free
Launch Team / Built With
Shram
Shram
@jay_gadekar so excited to have built it alongside you and our team! <3
Nice product! The on-device, you-pick-what-it-sees approach is the part that I think makes this actually look really usable. I spend my time in the Claude ecosystem too (building governance tooling around skills/access), so the granular per-app control especially caught my eye. Quick question: when you pause it or revoke an app, does the context it already captured from that app stay in the local store, or get dropped?
Shram
@tom_palmer_ux - thanks for writing back. When you pause - say for 5 or 10 min, your memory won't be created for that duration. Please feel free to ask more queries. Good day! :)
Shram
@tom_palmer_ux thank you for trying out Minimi! Please share your feedback with us soon :)
Shram
Minimi is the most delightful part of my day. It has even made me a better, more thoughtful gifter haha 😛
SUPER stoked that others can now play around with it.
Here are some fun and work related things you can try doing!
Fun
"What should I get Jay for his birthday?" and it actually knows, because it remembers the offhand thing he wanted three weeks ago on a call.
"What was that restaurant someone raved about last month?" No idea who, no idea when. Minimi finds it.
"Recommend a movie for tonight" and the pick actually is awesome, because it knows what I've genuinely been into lately.
Work
"Draft a follow-up from my call with Niket" and it pulls exactly what we discussed.
"What did we decide about the UX copy?" answered in one line, across scattered Slack threads, docs, and calls.
"Catch me up on what I missed" after a long deep work session, so I walk back in already knowing where things stand.
Do try and let me know what you built <3
@ojasvika_sahu the gift example — remembering an offhand thing someone said on a call weeks later — is exactly the magic tbh. but if its hearing everythiing, how does it know that one line mattered vs the 99% thats just background chatter? curious if thats tuned or you just store it all and let retrieval sort it out
Shram
@haotian_wang5 the retrieval is just the magic. We have built SOTA memory - it has beat the published benchmark of 0.36 (BEAM) by 50% - that is why the results are really on point!
Shram
@ojasvika_sahu - yup! Proud to have built this together :))
Writee AI
Have been lucky to get early access to Minimi and my god it’s powerful! From getting random, small insights that I forgot from my meetings to tracking my work output to remembering things that I did 2 weeks ago. Minimi is like magic
Shram
@prannay_kedia your initial feedback was critical for us to build ahead. Thank you for supporting us so early on!
Shram
@prannay_kedia - thanks Prannay for being amongst our earliest users!
Shram
The fun technical bit: it's all local-first. Your context gets embedded and stored on your Mac, retrieval runs locally, and Claude pulls it over a single MCP connector. Nothing leaves your device. I know because I built it :))
Shram
@vineet_gupta20 - great job, Vineet :))
Congrats on the launch @jay_gadekar @ojasvika_sahu ! upvoted!
Question: will it bloat the claude memory & increase the tokens used over time?
Shram
@aiswarya_s - thank you! Claude retrieves data from your on-device memory only when you prompt it, so we don't directly bloat its memory. Once Claude has seen the data, it remembers it in its own persistent memory.
Token usage increasing over time is a fair concern - but we continuously optimise our memory layer to prevent that. We also benchmark 50% better than the current SOTA on the BEAM benchmark, which means our memory layer is extremely efficient at both creating embeddings and retrieval. Token usage stays lean by design.
Do try Minimi and stay in touch. Good day! :)
Congrats on the launch. Most memory tools that 'always listen' wave their hands at the delete path, so I went looking for it here. When I revoke an app or delete a memory, do the vectors already sitting in the local store actually go? That's the real privacy question I believe for something that's on by default