Launched this week
Memoriq
Your private AI memory for ChatGPT, Claude, Gemini and Grok
196 followers
Your private AI memory for ChatGPT, Claude, Gemini and Grok
196 followers
Memoriq is your private AI memory for ChatGPT, Claude, Gemini and Grok. Save the conversations that matter in an end-to-end encrypted vault that only you can access. Open source, self-hostable, and built for people who don't want to lose valuable AI chats or trust another plaintext cloud service. Search, organize, and keep your AI knowledge under your control.
I bounce between Claude and ChatGPT depending on the task and re-explaining my project context every time gets old fast. A shared memory layer makes sense in theory, but I'd want to know how it decides what's worth remembering vs noise. Is that automatic or do you curate it yourself?
Multiavatar in Solidity
@josedamian Right now, it's user-curated rather than automatic. The idea is that you save the conversations you know you'll want later instead of having another AI guess what's important and what's noise.
Automatic memory is an interesting idea, but I think the right starting point is giving people a private place to save the conversations they care about.
@giekaton That tracks — I'd rather decide myself than have another AI quietly filtering what it thinks matters. Curious if curation gets easier over time or if it stays manual no matter how much you use it.
The cross-model angle is the interesting part. Most memory layers quietly lock you into one assistant. Curious how you handle conflicting facts when the same memory gets updated differently across tools, is it last write wins or something smarter?
Multiavatar in Solidity
@ddante216 Thanks for the question! Right now, Memoriq doesn't try to merge or reconcile memories across models. It preserves the original conversations, so conflicting information can coexist and you decide what's relevant.
That makes sense, and honestly it is the more trustworthy call. Letting conflicts coexist and keeping the human as the one who decides beats silent auto-merging, which is where a lot of memory tools quietly lose people. Appreciate the thoughtful answer, wishing you a strong launch.
End-to-end encrypted AI memory is a strong position. A lot of useful thinking now lives inside chats and gets lost fast. How are you approaching search: semantic recall, folder-style organization, or both?
Multiavatar in Solidity
@sarveshsea Right now, the focus is on folder-style organization and fast search across your saved conversations. Semantic search is something I'd love to experiment with as the project evolves.
Works like a charm with ChatGPT when saving to my Memoriq account. But I can't seem to find out how to use the local save option instead.
Multiavatar in Solidity
@anthony_sanna1 Glad to hear it's working well with ChatGPT! If by "local" you mean self-hosting, you can run your own Memoriq instance by cloning the GitHub repo and following the setup instructions.
Mailwarm
How does capture work across ChatGPT and Claude, is it a browser extension or do you import exports?
Multiavatar in Solidity
@thamibenjelloun Right now, capture works through the browser extension or by manually copying and pasting individual chats. Supporting chat imports is definitely something to consider for the future.