hydramem is an open-source library that provides local, privacy-first long-term memory for AI agents. It combines hybrid graph and vector search, two-stage verification, and autonomous maintenance to help developers build agents with persistent, efficient, and private memory storage. Ideal for AI developers focused on privacy and autonomy.
hydramem is a RAG, search & retrieval project. It focuses on enabling AI agents to store and retrieve long-term memory locally with privacy and efficient search. hydramem is an open-source project aimed at AI developers building autonomous agents. hydramem is open source under the MIT license. hydramem is available on the command line, and it can be self-hosted.
Behind hydramem is xusliebana, and it first shipped in 2026. The project is developed in the open on GitHub with 11 commits in the last 90 days. Key capabilities include hybrid search, graph database, and vector search.
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