Unabyss
MCP-native self-updating context layer for your AI
Start new thread

Unabyss for Claude - Shared memory across all apps and LLMs. In Claude

by•
Claude doesn't know what happens in GPT. Neither one really knows who you are or what your company does. Now they can. Unabyss gives Claude memories from your other AI agents and everyday apps: email, Drive, GitHub, Notion, meeting recorders, and 20+ more. It saves new memories too, so GPT and Cursor stay in sync with the exact same context - sharper than wiring each tool into Claude one by one. Finally, a real memory that follows you. Private. Portable.

Add a comment

Replies

Best

Shared memory sounds simple until two apps write conflicting facts about the same user and the model has to reconcile them. How are you handling write conflicts and stale context across sources? That is where most memory layers break down under real usage. Good problem to be working on.

Maker

 totally agree! Unabyss executes conflict resolution just before retrieval, so any potentially incorrect fact is checked against other memories, with recency taken into account. Outdated or incorrect information are simply filtered out before being returned.

And btw this is a core part of our memory architecture, and we're improving it every day. Literally!

How do you ensure that Claude & ChatGPT have the same memory? And does it work for OpenClaw too?

Maker

 

Everything happens via our "store" tool in memory. You can save every conversation to Unabyss - just call it manually (e.g. "save it to Unabyss") or adjust your e.g. Claude preferences so that every chat is saved to your memory.

Some users choose the 1st option, some the latter - depending on how much information they want to transfer to Unabyss.

And yes, it works for OpenClaw too! In general, it works with every AI tool that has MCP :)

Maker

 when you are onboarding a new agent to Unabyss, there is a short setup/onboring flow that allows you to pick what you want to save. Based on that, you get global instructions that you can paste in your preferences - this way, context always flows between agents effortlessly.

Nice idea. Congratulations!

How easy is it to clean up or remove memories if something gets saved by mistake?

Maker

 extremely easy :)

if something gets saved by mistake, you can ask Unabyss to edit/remove it wherever you use it (Claude, GPT, Cursor, or in Unabyss itself :))

and you want to know what Unabyss knows about specific topic - you can talk it through. And (on Monday) we'll release Context View, where you'll see every information that Unabyss has!

Maker

 super easy, there are 2 main ways in which you can do it: talk to our context agent in the app or do the same in your Claude, ChatGPT, or Hermes. Once you adjust it, it will stay fixed in your context.

the onboarding flow for picking which apps to sync feels really thoughtful, especially how you can preview exactly what each AI will see before sharing. nice touch.

Maker

 

Thanks! That's one of the changes we've introduced after feedback from our users - glad to see it improves your experience :)

Maker

 thanks! feel free to share your feedback anytime ;)

Strong idea - managing the agent memories is far from obvious.

Maker

 thanks! We think we know how to crack it ;)

I'm a designer, can I use it for multiple clients branding guidelines and other context?

Maker

 yes! you can connect it to our Notion board with the client list, Gmail, and Calendar to get the full context, and then use it in Claude to get whatever you need!

Congratulations on the launch! Is there a way to whitelist/filter certain apps? What I meant to say I do wanna connect notion/google meet but want to filter it out from certain documents or meets. so that it don't sync everything to claude.

Maker

 Thanks! Every time you connect a new agent to Unabyss, you can select what this agent will get. You can give it full context access or filter out confidential information, personal or business, but you can also filter out context that was fetched from the chosen app.

Congrats on the launch! The re-explaining problem is so real, I probably retype the same company context into AI tools five times a day. Curious how you handle context that goes stale, like if my role or product changes, does Unabyss detect that from my connected apps and update automatically, or do I need to correct it manually?

Maker

 Thanks! About your question: every time a new item is fetched from the connected app, it is analyzed against the current context. Unabyss checks for conflicts, dates, and identities - if new data is better used to update an existing entity than to create a new one, the update will happen. This ensures that the context is always up to date.

Legit ran into this issue when Launch QA time came up. Lots of missing pieces where I had to hunt down to double check items. This looks slick.

Maker

 thanks! With unabyss this should never happen again ;)

Good luck with the launch you guys

Maker

 thanks a lot!

First
Previous
123
•••
Next