Memmy Agent - Let every AI remember the same you.

@mcarmonas Thanks Martí — just had a look at Humalike. The turn-taking and social memory angle is really interesting.

We’re approaching memory from the cross-agent side, so there’s probably a lot for us to compare notes on — especially around Hermes :)

@mcarmonas Thanks so much! Personal memory is right at the heart of what we’re building too — love that humalike.ai cares about the same thing. Would be great to exchange notes sometime :))

@gapostolov this is such a lovely surprise — thank you so much! 🙌
Really appreciate you taking the time to make a live demo for us. That honestly means a lot, especially on launch day. We’ll definitely check it out!

@gapostolov Thanks so much! Glad this resonates with you — that’s exactly what Memmy is built for: keeping your context with you across devices and tools, so every AI remembers the same you.

Appreciate you making the livedemo too, just checked it out — really cool. Thanks for the support!

@sky_heartfly Memmy is MIT-licensed, so yes, commercial use is allowed. You’re free to use, modify, and distribute it, as long as you keep the original copyright and license notice. No extra commercial restrictions from us.

@sky_heartflyMemmy is MIT-licensed, so yes, commercial use is allowed. You’re free to use, modify, and distribute it, as long as you keep the original copyright and license notice. No extra commercial restrictions from us. As usual with open source, third-party dependencies keep their own licenses — worth a quick check if your company has a compliance process. Happy to clarify further!

@aren_barseghyan Thanks so much! That’s exactly the pain Memmy is built for — so you don’t have to re-explain your project every time you switch tools. Glad it fits your workflow. Thanks for the support!

@aren_barseghyan Same here. that constant context reset was driving us nuts toooooo... What tools are you bouncing between most these days? Curious where the handoff gets the messiest.

@blink_66 Not yet. Right now, all connected agents share one memory pool.

Separate memory spaces and per-agent access control are on our roadmap though — especially for people juggling work, personal, etc.

For now, separate Memmy instances are the cleanest workaround.

@reda_roqai_chaoui Fair question. If you mostly use one assistant, its built-in memory is probably enough.

The problem starts when your work is split across Claude Code, Cursor, Codex, and a few other tools. They all know different pieces of the story. Memmy gives them one shared memory, stored locally, so you’re not rebuilding context every time you switch.

That’s really the main difference: built-in memory stays inside one product, while Memmy follows you across agents.

@luke_pioneero It doesn’t simply overwrite the old memory. When a decision changes, Memmy keeps the original context as an L1 trace and can create a decision-repair record that feeds into updated L2 guidance. So the history is preserved, while later retrieval can work from the revised decision instead of treating both versions as equally valid.

You can also inspect and delete memories yourself. What we don’t have yet is a polished side-by-side conflict review flow — that part is still being improved.

@luke_pioneero yeeeeah! that is the part we care most about. Models and tools will keep changing, every month even week have different agents and models. but your context shouldn’t reset every time you switch!

@alex_watson2110 yeah, stale-but-confident memory is the much harder problem.

When Memmy catches an explicit correction, it can create a decision-repair record and update the guidance built from that memory, rather than just storing two conflicting versions side by side. We still keep the original trace for provenance.

The part we’re improving now is making those conflicts easier to spot and review, instead of resolving everything silently in the background.

@carlvert Memmy doesn’t dump the whole memory store into the prompt.

It searches across vector, full-text, pattern, and structural signals in parallel, merges the candidates, then applies relevance thresholds, dedup, and MMR to avoid near-duplicates. A final LLM filter trims the set again — up to 8 memories by default.

Each injected snippet is capped too, and Skills go in as short summaries unless full mode is needed. So the idea is broad recall first, then keep the actual context block small. You can also inspect what was considered, kept, and injected in the retrieval logs.