Memmy Agent

Let every AI remember the same you.

Productivity

Open Source

Artificial Intelligence

Visit WebsiteSee on Product HuntTwitter ⧉Github ⧉

I think I saw a similar service just a few days ago... Do you have a B2B offering? For example, so other AI services could integrate with your platform and get more information about their users?

I really like the idea of giving different AI tools a shared memory instead of starting from scratch every time. Local-first is also a big plus. Feels like a very practical approach!

Letting external agents both read memory and write new experience back closes the loop beautifully. That is what real continuity needs.

Oh this would be life-changing! I am curious, though, does this help Claude Code, etc., identify the right pieces of memory? Often, I've noticed that these AI models latch onto some obscure instance in the past and make decisions based on it. How do you ensure the memory being accessed is always relevant?

Just launched, and we’d love people to actually use it for a day — not only read the pitch.

A simple try path: install Memmy → connect the agents you already live in → scan your existing chat history → then work as usual. See whether the right preferences and project context follow you when you switch tools. Also peek at the local memory panel: what’s getting captured, and can you delete what shouldn’t be there.

We’re especially hungry for this kind of feedback: which workflows feel instantly worth it, where recall misses, and which tools you want first. Drop it in the PH comments or ping us directly — treat today like open-box day, and help us sharpen cross-agent memory together ✨

https://memmy.bot/

We built Memmy for a pretty simple reason: we were hopping between Cursor, Claude Code, and Codex too — and every switch meant re-explaining project context, preferences, and the last landmines we hit. Exhausting.

So we made a local shared memory layer: different agents read and write the same context, and the data stays on your machine by default. After install you can scan the history you already have, so you’re not starting from an empty box; then it keeps capturing and recalling as you work.

If “switch tools, lose the plot” sounds familiar, come try it. Love it, hate it, find something weird — tell us. Real feedback is how we ship 🙌

https://memmy.bot/

Local SQLite storage plus user-controlled access makes the privacy story easy to understand. I appreciate the concrete implementation details.

Local note apps preserve information, but they do not automatically surface the right decision to the agent working on today's task.

Retrieval analytics showing which memories helped, were ignored, or caused corrections could improve both user control and system quality.

I’d use this to keep my writing voice consistent across different AI tools. They all seem to understand my style eventually… right before I start a new chat

Referencing API keys through environment variables instead of hardcoding them in config is exactly the kind of secure default I want.

Been looking for something like this, using claude_mem skill up to now.
Amazing!

Could definitely see this being used for shopping or booking flights. I want my agent to just remember my preferences and what I like in terms of clothes and flight selections for example.

Interesting thought: could a team use Memmy to help onboard new hires? There’s so much useful context that never makes it into the official docs.

local-first with no cloud is exactly why i clicked too, but what happens on a new machine? does the memory pool migrate somehow or does a laptop swap just reset you to zero. that tradeoff between local-only and continuity feels like the real design fork here

Memory with agentic flows is often a gap when I’ve tried my own experiments, looking forward to checking this out!