Claude only! SCMD is an open-source, local review deck for the persistent memories Claude Code saves about you and your projects. Keep, delete, skip, undo, rewrite, and inspect why a memory was saved. Decisions stay staged until you confirm; deletes go to restorable trash. No telemetry, no cloud service, and zero npm dependencies. Run it with /scmd:run or npx. MIT-licensed and ready for contributors.
So my wife found out that someone named Claude was calling me "Daddy". After a lot of explanation... I built SCMD(Stop Calling Me Daddy). It turns out it stored a memory that I didn't remember.
SCMD is a simple tool that helps you Review and Manage your Claude memories.
SCMD turns that into a local review deck:
- Keep, delete, skip, or undo
- See why a memory was saved
- Rewrite it with your local Claude Code CLI or edit by hand
- Review the full batch before anything changes
- Restore deleted memories from local trash
It runs on localhost, has zero npm dependencies, and has no telemetry. Nothing goes to an SCMD service. If you request a rewrite, the text goes through your own logged-in Claude Code CLI.
Try it from a terminal:
`npx -y @nelsonjohnsolo/scmd`
Or install the Claude Code plugin and run `/scmd:run`.
SCMD is MIT-licensed. The repository is open for issues and focused pull requests. I’m especially interested in real-world memory formats, Windows and Git Bash edge cases, accessibility improvements, and ways to make the review flow even simpler.
nice product, and thanks for having shared it with a MIT license. it's less and less common recently
staging decisions until you confirm and sending deletes to a restorable trash is such a thoughtful default for something that edits what claude "knows" about you. the "why was this saved" view is the bit I'd use most. do you plan to support other agents' memory files too, or stay claude only on purpose?
the origin story alone is worth the upvote. I've got my own memory file system going for Claude Code and honestly I've never actually gone back to audit what's in there, I just trust it's fine, which is exactly the kind of assumption your wife's discovery proves wrong. does SCMD review memories written by custom memory setups too, or is it scoped to Claude Code's own built-in memory feature specifically?
How does the review deck handle memories that are related to multiple projects?
About SCMD on Product Hunt
“Manage what Claude Remembers and Keeps as Memory.”
SCMD launched on Product Hunt on October 3rd, 2026 and earned 95 upvotes and 8 comments, placing #8 on the daily leaderboard. Claude only! SCMD is an open-source, local review deck for the persistent memories Claude Code saves about you and your projects. Keep, delete, skip, undo, rewrite, and inspect why a memory was saved. Decisions stay staged until you confirm; deletes go to restorable trash. No telemetry, no cloud service, and zero npm dependencies. Run it with /scmd:run or npx. MIT-licensed and ready for contributors.
SCMD was featured in Open Source (69k followers), Developer Tools (521.5k followers), Artificial Intelligence (481.6k followers) and GitHub (41.4k followers) on Product Hunt. Together, these topics include over 269.3k products, making this a competitive space to launch in.
Who hunted SCMD ?
SCMD was hunted by Nelson John. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how SCMD stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Nelson John