Launched this week
Memmy Agent
Let every AI remember the same you.
1K followers
Let every AI remember the same you.
1K followers
🍙 Memmy Agent is a personal memory hub and local AI agent for all AI Agent and tools like Claude Code, Codex, OpenClaw and Hermes. Gives every AI one shared, full-controlled memory — they all remember the same you. Memmy turns chats, decisions, prefs, progresses, and experiences into long-term memory, brings the right context into matching task, also can take on work directly. Local-first by default. Your memory stay under your control: manage them anytime. Free start with 2M ChatGPT tokens.
Shared memory across agents sounds powerful, especially with per-tool control. Can I create separate memory spaces for work, personal projects, and clients—and decide exactly which agent can access each one?
Memmy Agent
@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.
@yunn_chen Got it, thanks for clarifying!
@yunn_chen Separate Memmy instances sound like a practical workaround for now. I’m glad granular memory spaces and per-agent access controls are on the roadmap—those would make managing client and personal data much safer and more flexible. Looking forward to it!
Memmy Agent
@blink_66 yeaaah, shared memory is useful, but once client data is involved, the boundaries need to be much more explicit. Granular spaces and per-agent access controls are definitely an important next step for us. Thanks for the thoughtful feedback — really appreciate it.
Memmy Agent
@yunn_chen @blink_66 Appreciate you looping back — use cases like yours are exactly why isolation is high on the list. We’ll keep shipping toward that 🙌
For me, the interesting challenge isn’t whether an AI can remember more, but whether it can remember the right things. How does Memmy distinguish a durable preference from a one-time instruction?
Memmy Agent
@orman_canida That’s the hard part. Memmy doesn’t treat every instruction as a permanent preference.
A one-off “use X for this task” stays with that task. Clear signals like “I prefer X,” “next time do Y,” or “use X instead of Y” can become preference memory, and repeated patterns across different tasks add stronger evidence over time.
So it’s a mix of what you explicitly say and what keeps showing up—not just remembering every command forever.
@yunn_chen That makes sense. The repeated-pattern signal is especially interesting. How does Memmy handle it when preferences change over time—can users see and correct what it has inferred?
Memmy Agent
@orman_canida Hi, Canida. Preferences aren’t locked forever. As your behavior changes, newer patterns gain weight and older ones decay or get archived. You can also open the Memory panel to review what Memmy has inferred and delete anything that no longer fits. You’re always in control.
Interesting idea, you have my upvote. What are the current limitations?
Memmy Agent
@martin_yochev1 Thanks for the upvote! A few honest limitations right now:
Desktop is macOS / Windows — Linux desktop isn’t there yet (CLI/from source can still work on Node).
Local-first — memory lives on your machine by default; multi-device sync isn’t a built-in cloud product yet.
Free trial tokens are limited — great for getting started; heavier daily use usually means switching to BYOK.
If you hit a specific workflow limit, tell us — that’s the best way we prioritize.
Memmy Agent
@martin_yochev1 Appreciate the upvote! Those are the main current limits — if a specific workflow is blocked for you, shout and we’ll prioritize from real usage 🙌
Memmy Agent
Thank you for the upvote! The main limitations today are around the parts we’re still actively refining: more granular memory spaces, per-agent access controls, and richer conflict handling when newer decisions replace older ones.
For now, separate Memmy instances are the safest way to keep unrelated contexts isolated. We’d also love for you to try the TUI—it’s already quite capable, and we put a lot of care into making the interface feel friendly and fun to use. Feedback from real workflows would be incredibly helpful.
Referencing API keys through environment variables instead of hardcoding them in config is exactly the kind of secure default I want.
Memmy Agent
@1251912798 Glad that stood out. ✌️ The boring security details matter a lot once an agent starts touching real work. We’re trying to make the safer path the default, not something you have to remember to fix later.
Memmy Agent
@1251912798 +1 — Pema said it perfectly. Love that this detail stood out to you 🙌
Memmy Agent
@1251912798 Thanks! Secure defaults should feel boring in the best way — less “remember to harden it later,” more safe out of the box 🔐
Memmy Agent
@1251912798 Secure defaults should make the safe path the easiest path. Keeping API keys out of configuration files reduces the risk of accidental exposure and makes credentials easier to manage across environments. We’re working to support environment-variable references as soon as possible.
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?
Memmy Agent
@natalia_iankovych Yeah — other AI products can plug into Memmy through the API or CLI. The important part for us is that the user stays in control, rather than apps quietly building another profile behind the scenes.
The fuller B2B stack is more on the MemOS side, though the hosted version isn’t broadly available overseas yet. Curious what kind of product you’d want to plug it into — and would love your upvote if the direction clicks 🙌
Memmy Agent
@naveenm7 Yep, that’s the obvious next step. Right now, switching devices means manually bringing the local memory database with you — there’s no seamless sync yet.
We’re planning an optional remote store, but we don’t want cloud to become mandatory just to get continuity. Your phone → Claude Code example is pretty much the use case. Would love your upvote, and definitely kick the tires on the local version meanwhile.
What makes someone use Memmy instead of just relying on Claude or ChatGPT's built-in memory?
Memmy Agent
@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.
Memmy Agent
@reda_roqai_chaoui I’d add: if you bounce between a few AI tools, built-in memory usually can’t follow you. Memmy’s bet is one shared local memory across them 🙌
Memmy Agent
@reda_roqai_chaoui +1 to Pema & Grace. The other piece for me: Memmy turns scattered chats into reusable experience, not just saved notes.
What’s your usual stack — Claude + Cursor, or more than that?