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

Unabyss 1.1

by•

Hey everyone 👋

Since the launch, we went heads-down and shipped a batch of improvements. Quick rundown:

  • Imports improved - both in terms of reliability and efficiency. The big one. If you tried Unabyss early and a source synced halfway or dropped data, that's fixed. Every import runs clean. And we’re able to build even more detailed context for you.

  • Better cross-agent memory. We upgraded the store tool in our MCP - so if you run more than one agent, they finally share context. What you tell Claude, ChatGPT picks up too. No more re-explaining yourself to every assistant.

  • New integrations - we’ve added 20+ integrations (CRMs, project management tools, ads managers, and more). More sources you can pull context from. Open your Unabyss and check the connections - the new ones are there, ready to use.

  • Skills, built into the MCP. Ready-made playbooks that handle the repetitive parts of your day, right inside the MCP. Both our and forks of the most popular skills that could use some context :) Worth a look - a few will probably become habits.

That's the short version. If something feels off or something is missing, drop it below!

49 views

Add a comment

Replies

Best

Nice, the cross-agent memory thing actually sounds the most useful here tbh.

curious how you handle consistency tho, like when different integrations bring conflicting data (CRM vs ads vs notes). does the system try to rank sources or just merge everything as-is?

 we rank multiple factors - e.g. data source (e.g. it comes from an email or notion page), date of data ingest, and more - to get the full picture.

on my example - you can imagine that as an early-stage startup we do a lot of strategy changes - Unabyss is able to grasp the current strategy, but also understand what it looked like before the change & gives the full context to AI when needed :)