PeppermintDownload for macOSThe pricing stays simple: one plan for yourself, one for teams, and one for larger deployments that need more structure.
Beta access
The plans are here so you can see where Peppermint is headed. For now, download the Mac app and use Peppermint free while we keep building.
Download for macOSFAQ
A few of the things people ask before they trust a memory layer with the thread behind their work.
Not really. Peppermint is the memory layer underneath the model. It turns the thread behind your work into usable memory, facts, summaries, and routines so Slack, Claude Code, Codex, Linear, or the next tool can work from real context instead of a blank box.
The MCP server exposes your memory store: searchable memories, structured facts, daily summaries, collections, preferences, routines, and permissioned team context. In practice, that means another tool can ask for the thread behind the work instead of making you restate it from scratch.
Your memory starts personal. Shared context is permissioned. You decide which replies, summaries, and handoffs leave your private memory layer and which ones stay with you.
Claude and Codex are great interfaces, but they do not keep the ongoing state of your work unless you keep feeding it back in. Peppermint keeps that state intact across tools, so the interface can change without the memory disappearing.
That is the point of the product. The memory stays with Peppermint, not with a single interface. You can move from Slack to Docs, from Linear to Claude Code, or from Codex to whatever comes next without rebuilding the story every time.
Peppermint is designed to run quietly in the background. The goal is to feel like part of your desktop, not another heavy app fighting for attention.