MUSE is an open-source, zero-dependency Markdown system for governing AI coding assistants. It provides persistent short- and long-term memory, role isolation, directive queues, skills, and commands such as resume, save, and distill for developers working across AI coding tools.
In the Memory & skills space, MUSE takes a focused approach. It focuses on preventing AI coding assistants from losing project context, role boundaries, and lessons between conversations. It is built as an open-source project for developers using AI coding assistants. The project is open source (MIT). MUSE is available on the web and the command line, and it can be self-hosted.
Myths Labs builds and maintains MUSE, and it first shipped in 2026. Development happens publicly on GitHub with 30 stars and 2 commits in the last 90 days. Among its 9 catalogued features are persistent memory, daily logs, and role isolation.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do