Audit and switch off Claude Code memory
Technique
Claude Code can store 'memories' about your projects. This skill is checking what it has stored, then turning the feature off, archiving the memories and deleting them. Useful when you want clean, repeatable runs.
Theo's current stance
After reading his memories, Theo called the feature garbage. He reruns tasks to test new models, and saved memories make those tests 'less pure'.
Try it
- Ask Claude Code: 'What memories do you have of this project?'
- Ask how often those memories are read in sessions versus written.
- Have your agent disable memory, archive the existing files, then delete them.
First seen
21:08
is slop. Okay, I'm going to have Fable go across my fleet, disable memory and cloud code across all of the machines, archive the ones that I have, label them correctly, and then delete the memories because I have concluded this is absolute [ __ ] garbage. I knew it
Every mention
21:08
is slop. Okay, I'm going to have Fable go across my fleet, disable memory and cloud code across all of the machines, archive the ones that I have, label them correctly, and then delete the memories because I have concluded this is absolute [ __ ] garbage. I knew it
15:37
garbage. Okay, this one's annoying because I do the ping round modernizations to test new models. So if it is storing these things in memory, that makes that test less pure and really annoying. Benchmarks, I want LM
Theo Daily is unofficial and not affiliated with Theo or t3.gg. Written by Claude Opus 5.5 from each video's transcript.