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.
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 :))
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
@artstavenka1 - great question, and you're right to push on this. When you block an app or domain, Minimi stops capturing from it going forward. Revoking or pausing fully stops all capture.
On deletion - you can't yet delete specific memories granularly, but a full app uninstall wipes the local store entirely, vectors included. Selective memory deletion is on our roadmap.
@artstavenka1 Great question. It stops creating memory after you pause Minimi or block an app. The earlier memory stays but we are planning to allow selective deletion.
the context bottleneck is real. most bad AI output i see is a missing-context problem, not a model problem, so this direction makes a lot of sense. the part id be curious about is signal vs noise. passively capturing everything across docs/calls/tabs is powerful, but the risk is feeding Claude confidently-irrelevant context. how you decide what's actually worth surfacing feels like the real moat here. on-device + private is a smart trust call too. nice work.
In Minimi - updates, contradictions, and temporal order are handled as core behavior, not patched on.
It's why we measure ourselves on BEAM rather than the older recall-only benchmarks. BEAM runs at 1M and 10M token scale and can't be solved by a bigger context window, so it directly tests the staleness question.
We're at 54% vs the prior 36% SOTA, with most of the lead on the over-time tasks.
Short version: maintaining an accurate picture beats retrieving more, every time!
@ozandag Anyone can capture everything; the value is in what you choose to surface. We optimize for an accurate picture over raw recall, which is why we benchmark on BEAM and LongMemEval rather than recall-only tests — these run on very long conversations where the retrieval system has to surface only the relevant pieces. And keeping it on-device.
@ozandag You've named the actual hard problem. Capturing everything is easy. Knowing what's relevant to this conversation is the work.
The way we handle it: Minimi doesn't dump everything into Claude's context. It retrieves based on what you're currently doing - the app you're in, the conversation you're having, the doc you're editing. The surface area Claude sees is narrow and intentional, not a firehose.
The deeper moat is temporal + behavioural signal - what you've engaged with recently, what you keep returning to, what you've explicitly acted on. That's what separates useful context from noise. Still building on this, but it's the core of what makes the benchmark results hold up in practice.
Honestly....I was so tired of giving my LLM context about everything I was working on 😣 My projects, stuff about myself, my choices, my working patterns, pasting screenshots from old chats, sharing the same docs again and again.
Minimi SOLVES ALL OF IT. No need to give any context to your LLM about what you're working on or your past conversations. It captures it all, everything on your screen, and keeps the data on your device, so it's completely safe and local. If you live inside your LLM, this is the upgrade you didn't know you needed.
@dynatrading Hi Andy - the infrastructure we rely on - Accessibility - is not currently reliable for Windows, thus we have not gotten around making a windows version.
However building ambient memory for Windows is something we are absolutely going to get on very soon!
@dynatrading We went Mac-first to get the capture quality right every app, zero integrations, completely passive. Replicating that on Windows takes time to do properly.
@dynatrading The re-explaining tax is real - most people just accept it as part of using AI. It shouldn't be.
On Windows - Mac-first was a deliberate call, not a limitation. The on-device architecture we've built runs close to the OS in ways that need platform-specific work. Windows is on the roadmap but we want to do it right. :)
Many people already try “memory” via manual notes or lightweight MCP memory servers. What’s the key product bet behind ambient capture across tabs/docs/messages/calls—and where does that approach win or lose versus a more intentional, user-curated memory workflow?
Manual notes and curated workflows ask you to decide what matters in the moment. Which means you're one busy day away from a gap. Most people don't take notes on the tab they skimmed or the offhand thing mentioned on a call - but that's exactly the context Claude ends up needing.
Ambient capture removes the decision. You don't curate, you just work - and Minimi builds the picture in the background.
Intentional memory is great for things you know you'll need. But most context isn't that - it's just ambient. That's the gap.
@curiouskitty Manual/Curates memory/workflow will miss out on things by default. Humans aren't perfect and hence Minimi ambiently capturing everything helps.
Report
Wow. This is exactly what I need. Will come back and ask questions but excited to check this out!
Replies
minimi
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 :))
minimi
@vineet_gupta20 - great job, Vineet :))
minimi
@vineet_gupta20 Being local is a big relief!
FastCut
Super cool product. Congrats on the launch team.
minimi
@nikhilsheoran - thank you! Do share feedback :)
minimi
@nikhilsheoran looking forward to hearing your feedback!
minimi
@nikhilsheoran Thanks, Nikhil!
minimi
@nikhilsheoran thanks
WriteMyPRD
minimi
@suhasmotwani Thanks as always Suhas! <3
minimi
@suhasmotwani - thank you! Do try using and share more feedback :)
minimi
@suhasmotwani Thanks Suhas!
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
minimi
@artstavenka1 - great question, and you're right to push on this. When you block an app or domain, Minimi stops capturing from it going forward. Revoking or pausing fully stops all capture.
On deletion - you can't yet delete specific memories granularly, but a full app uninstall wipes the local store entirely, vectors included. Selective memory deletion is on our roadmap.
Keen to hear your feedback once you've tried it.
minimi
@artstavenka1 Great question. It stops creating memory after you pause Minimi or block an app. The earlier memory stays but we are planning to allow selective deletion.
AISA (aisa.to) AI Fluency Assessment
the context bottleneck is real. most bad AI output i see is a missing-context problem, not a model problem, so this direction makes a lot of sense. the part id be curious about is signal vs noise. passively capturing everything across docs/calls/tabs is powerful, but the risk is feeding Claude confidently-irrelevant context. how you decide what's actually worth surfacing feels like the real moat here. on-device + private is a smart trust call too. nice work.
minimi
@ozandag Hi Ozan, even @zaid_mallik1 asked me the same question!
Here was my answer:
minimi
@ozandag Anyone can capture everything; the value is in what you choose to surface. We optimize for an accurate picture over raw recall, which is why we benchmark on BEAM and LongMemEval rather than recall-only tests — these run on very long conversations where the retrieval system has to surface only the relevant pieces. And keeping it on-device.
minimi
@ozandag We are super accurate with what to surface. The underlying tech of Minimi helps with the accuracy.
minimi
@ozandag Capturing everything is table stakes knowing what to show Claude, and when, is where it gets hard.
minimi
@ozandag You've named the actual hard problem. Capturing everything is easy. Knowing what's relevant to this conversation is the work.
The way we handle it: Minimi doesn't dump everything into Claude's context. It retrieves based on what you're currently doing - the app you're in, the conversation you're having, the doc you're editing. The surface area Claude sees is narrow and intentional, not a firehose.
The deeper moat is temporal + behavioural signal - what you've engaged with recently, what you keep returning to, what you've explicitly acted on. That's what separates useful context from noise. Still building on this, but it's the core of what makes the benchmark results hold up in practice.
minimi
Honestly....I was so tired of giving my LLM context about everything I was working on 😣
My projects, stuff about myself, my choices, my working patterns, pasting screenshots from old chats, sharing the same docs again and again.
Minimi SOLVES ALL OF IT. No need to give any context to your LLM about what you're working on or your past conversations. It captures it all, everything on your screen, and keeps the data on your device, so it's completely safe and local. If you live inside your LLM, this is the upgrade you didn't know you needed.
Do give this superpower tool a try ⚡️
minimi
@dhanishta_likhar - yup! Proud to have built this together :))
minimi
@dhanishta_likhar those daily reports you create via minimi are so awesome!
minimi
@dhanishta_likhar It indeed feels like Jarvis!
The "no re-explaining yourself" pain point is so real — I spend a chunk of every session giving Claude context it had yesterday.
Love the on-device angle too. Privacy-first local storage is the right call when your context includes work meetings and personal projects.
One question: any Windows roadmap? That's my main blocker for trying it today.
minimi
@dynatrading Hi Andy - the infrastructure we rely on - Accessibility - is not currently reliable for Windows, thus we have not gotten around making a windows version.
However building ambient memory for Windows is something we are absolutely going to get on very soon!
minimi
@dynatrading We went Mac-first to get the capture quality right every app, zero integrations, completely passive. Replicating that on Windows takes time to do properly.
minimi
@dynatrading Hopefully soon, Andy!
minimi
@dynatrading The re-explaining tax is real - most people just accept it as part of using AI. It shouldn't be.
On Windows - Mac-first was a deliberate call, not a limitation. The on-device architecture we've built runs close to the OS in ways that need platform-specific work. Windows is on the roadmap but we want to do it right. :)
minimi
@dynatrading we went Mac first to get the capture quality right. Would love your feedback when it lands!
Product Hunt
minimi
@curiouskitty - the bet is on zero friction.
Manual notes and curated workflows ask you to decide what matters in the moment. Which means you're one busy day away from a gap. Most people don't take notes on the tab they skimmed or the offhand thing mentioned on a call - but that's exactly the context Claude ends up needing.
Ambient capture removes the decision. You don't curate, you just work - and Minimi builds the picture in the background.
Intentional memory is great for things you know you'll need. But most context isn't that - it's just ambient. That's the gap.
minimi
@curiouskitty Manual/Curates memory/workflow will miss out on things by default. Humans aren't perfect and hence Minimi ambiently capturing everything helps.
Wow. This is exactly what I need. Will come back and ask questions but excited to check this out!
minimi
@jessica_w204 - glad to hear. Please feel free to reach out any time. Good day! :)
minimi
@jessica_w204 Looking forward to your feedback!
minimi
@jessica_w204 Love to hear it Jessica would love your feedback once you've tried it
Pawpal
so cool!!!!!!!! kudos to the team
minimi
@nainabajaj27 Thanks Naina!
minimi
@nainabajaj27 Thank you as always Naina <3
minimi
@nainabajaj27 Thanks Naina!
minimi
@nainabajaj27 - thanks Naina. Do try using Minimi. It's uber cool!