yggdrasil-memory is an open-source, local-first memory infrastructure designed for AI coding agents. It enables agents to share and persist context using the MCP protocol, with zero external dependencies. Ideal for developers building autonomous or collaborative AI agents requiring shared, durable memory.
In the Memory & skills space, yggdrasil-memory takes a focused approach. It focuses on providing a unified, durable memory layer for AI coding agents to share context and data locally. It is built as an open-source project for AI agent developers. The project is open source (AGPL-3.0). It ships for the command line, and it can be self-hosted.
VonderVuflya builds and maintains yggdrasil-memory, and it first shipped in 2026. Development happens publicly on GitHub with 14 stars and 119 commits in the last 90 days. Among its 5 catalogued features are shared memory, local-first, and zero-dependency. 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