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
Launched this week
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







Creatr
Top team, Top product.
Congrats on the launch guys!!!
Shram
@divyansh_shourie Hi Divyansh! Thank you for your kind words - looking forward to hearing your feedback on Minimi :)
Shram
@divyansh_shourie - thanks Divyansh :))
Shram
@divyansh_shourie Thank you, Divyansh!
Wow. This is exactly what I need. Will come back and ask questions but excited to check this out!
Shram
@jessica_w204 - glad to hear. Please feel free to reach out any time. Good day! :)
Shram
@jessica_w204 Looking forward to your feedback!
Shram
@jessica_w204 Love to hear it Jessica would love your feedback once you've tried it
Pawpal
so cool!!!!!!!! kudos to the team
Shram
@nainabajaj27 Thanks Naina!
Shram
@nainabajaj27 Thank you as always Naina <3
Shram
@nainabajaj27 Thanks Naina!
Shram
@nainabajaj27 - thanks Naina. Do try using Minimi. It's uber cool!
Fr. Giving context to every LLM for the same thing I had it do yesterday and the day before is frustrating. About time someone built a plug-and-play memory layer and relieved me of the annoying ritual. Great work, team. Rooting for you.
Shram
@kritarthmittal Thank you for trying out Minimi Kritarth! Really appreciate your support!
Shram
@kritarthmittal - thanks Kritarth - for always being a true believer in us. Hope you enjoy Minimi :)
Shram
@kritarthmittal Thanks, Kritarth!
WriteMyPRD
Shram
@suhasmotwani Thanks as always Suhas! <3
Shram
@suhasmotwani - thank you! Do try using and share more feedback :)
Shram
@suhasmotwani Thanks Suhas!
fixes the exact friction point of long-term AI usage. Forcing a local memory layer that connects straight to Claude's custom connector via a single link is brilliant design because it means no new app to live in. Running a deep work session and then just telling Claude to catch you up on what you missed across scattered docs and calls is exactly what real automation should look like. Great launch.