KHMS is a file-based know-how management system that gives LLM agents persistent long-term memory. Developers can install and use it as part of an agent workflow for retaining knowledge across sessions.
In the Memory & skills space, KHMS takes a focused approach. It focuses on giving LLM agents persistent, file-based memory across sessions. It is built as an open-source project for AI agent developers. It runs on the web and the command line, and it can be self-hosted.
It is developed by kostey. Among its 5 catalogued features are persistent memory, file-based storage, and know-how management.
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