How It Works

This shows you exactly what claude-mem is doing under the hood: capturing compressed observations from every Read, Edit, and Bash command, then auto-injecting relevant context into future sessions so you never re-explain your codebase. Memory kicks in on your second session in a project, and everything lives in ~/.claude-mem on your machine. The only network calls go to your configured AI provider for compression. It's the kind of explainer you'd want when a tool starts doing invisible things in the background and you need to know whether to trust it or rip it out.

skills.sh installs: 5.4K
GitHub stars: 115.5K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add thedotmack/claude-mem --skill how-it-works --agent claude-code

Installs into .claude/skills of the current project.

Files

How claude-mem works

What it does

While you work, an observer (a second agent) watches what your agent reads, edits and runs, and writes short notes about what mattered. Those notes are called observations. When a session ends, the observer writes a summary. When the next session starts, your agent gets a compact index of the observations that matter for this project and fetches full details only when it needs them.

So the next session starts where the last one left off: no re-explaining the codebase, no re-discovering decisions.

When it kicks in

Memory injection starts on your second session in a project.

The first session seeds memory as you work. To front-load a whole repo in one pass instead, run /learn-codebase (~5 minutes on a typical repo, optional).