Skip to main content

​
What is xysq?

xysq is a context engineering platform. You capture raw AI work: session transcripts from tools like Claude, Cursor, and ChatGPT, plus files you upload. The xysq Memory Engine distills that into your context lake. Your agents and your team read from the lake. When something in it is wrong, you correct it once and the engine applies the fix everywhere it matters. The flow, end to end:
Most memory systems accumulate. Yours should improve. That is the difference the engine is built around: every piece of context traces back to a verbatim source, every change lands as a diff you can read, and a correction is visible on the very next query.

​
The shape of it

Three terms carry the whole model:
  • Context lake. One per user or team. It holds everything the engine has distilled from your AI work, organized as context graphs.
  • Context graphs. A lake holds many of them: Personal (yours), Teams (shared with your team), and Agents (one per agent you run). An agent reads from one or many graphs, and writes to its own.
  • The xysq Memory Engine. The machinery underneath every graph. Immutable verbatim logs at the bottom. Distilled, readable pages on top. Every fact cites the log it came from, and no change happens outside a checked, recorded run.
Your AI tools connect over MCP. They push what happened, verbatim, and pull assembled context back. All the real work (extraction, deduplication, structuring, ranking) happens server-side in the engine, not in the tool.

​
Correct once, and it improves

When the engine has something wrong, you do not re-explain it in every session. You correct it once. One gated run retunes both how the knowledge is structured and how retrieval ranks it, and the fix is visible on the next query. Anything the engine cannot apply safely goes to your review queue instead of changing silently.

​
Ownership

Your lake is yours: inspect it, export it, delete it. Pages are plain markdown. Bring your own storage and private deployment are rolling out; that is the direction we are building, not a shipped guarantee yet.

​
Where to go next

Quickstart

Connect a tool, push a session, correct a fact. About ten minutes.

Concepts

The context lake, context graphs, and how the engine distills and improves.

MCP reference

The four tools: userinfo, push_context, pull_context, share_context.