This gives Claude persistent memory across conversations using a local SQLite database. It's straightforward: search for what you've stored, add new memories with tags, delete what you don't need. The full-text search means you can actually find things later, and you can attach images to memories. The real value is when you're working on a project over multiple sessions and don't want to keep re-explaining preferences, architectural decisions, or deployment commands. It pipes well with other tools and outputs JSON when you need it. Think of it as a notebook that Claude can read and write to, stored in `~/.mem/mem.db` on your machine.
- skills.sh installs
- 2.4K
- GitHub stars
- 6
- last updated
- Aug 21, 2026
Install
$ npx -y skills add runablehq/memory --skill mem --agent claude-codeInstalls into .claude/skills of the current project.
Files
mem — Agent Memory Store
A CLI tool for storing and retrieving memories with full-text search. Data is stored locally in ~/.mem/mem.db.
When to Use
- Remember user preferences, project decisions, important facts
- Store code snippets, commands, configurations for later recall
- Search your knowledge base before asking the user for information you may have stored
- Attach images (screenshots, diagrams) to memories
Commands
Three operators: (none) = recall, + = remember, - = forget.
Recall (search, list, get)
mem # list recent memories
mem "deploy" # full-text search
mem "database" --tag db # search filtered by tag
mem 7sjtNVyZrNIa # get full content by ID
mem --tag prefs # list filtered by tag
mem "api" --limit 5 --json # limit results, JSON output
mem --full # show full content for all
Remember
Sponsors
Details
- Repository
- github.com/runablehq/memory
- Categories
- Backend & APIs, Databases
