Varven

Blog

On AI memory, token efficiency, and running language models on your own hardware. RSS.

Tokens · 2026-07-28

Memory is the token optimisation nobody is doing

Re-explaining context every session is usually the largest line in a token bill.

Memory · 2026-07-28

How to make AI memory actually work

The failure mode of a memory system is not a full store. It is a store full of things that were true once.

Memory · 2026-07-28

What belongs in AI memory, and what ruins it

Most memory systems fail on the write path, not the read path. They store the wrong things, and no error is ever raised.

Local-first · 2026-07-28

Keeping AI memory on your own computer

Every product in this category is somebody else's server. There is another way, and a real trade-off attached to it.

MCP · 2026-07-28

Connecting memory to any assistant with MCP

One protocol, every client. And a handshake with seven steps, six of which fail silently.

Memory · 2026-07-28

Why your AI forgets everything between conversations

It is not a bug, and a bigger context window will not fix it.

Practice · 2026-07-28

How to stop re-explaining your project every session

The preamble you type without thinking is the thing worth writing down.

Three threads

Memory — what belongs in an assistant's memory, how it goes stale, and why storing everything makes retrieval worse. Start with how to make AI memory actually work.

Tokens — where context spend goes, and why the biggest saving is usually not sending it at all. Start with memory as a token strategy.

Local-first — running memory on hardware you own, and the trade-off that comes with it. Start with keeping AI memory on your own computer.