whetstone-mcp is a local Model Context Protocol (MCP) server that allows any skill or agent to learn from its own use. It provides memory, retrieval, and learning capabilities for AI agents. Distributed as an open-source Python package, it is aimed at developers building adaptive, learning-based agent systems.
whetstone-mcp sits in PulseGate's AI & ML category. It focuses on enabling AI skills and agents to continuously learn from usage via persistent memory and retrieval in a local MCP server. whetstone-mcp is an open-source project aimed at developers. The project is open source (MIT). It ships for the command line, and it can be self-hosted.
Behind whetstone-mcp is Hrudith L, and it first shipped in 2026. Among its 3 catalogued features are Local MCP Server, Skill Learning, and Memory Retrieval. It exposes integrations via an MCP server.
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