llm-memory-store provides a personal, local-first memory backend for LLM-powered applications and autonomous agents. It uses SQLite for storage and supports the Model Context Protocol (MCP) for seamless integration with agent frameworks. Designed for developers who want privacy-focused, offline-capable memory without relying on cloud services.
llm-memory-store is an AI & ML product. LLM agents and applications lacking persistent, local-first memory for conversations and knowledge. llm-memory-store is an open-source project aimed at developers. The project is open source (Apache-2.0). llm-memory-store is available on the command line, and it can be self-hosted.
Behind llm-memory-store is Manoj Pardeshi, based in Germany, and the product first shipped in 2026. Among its 4 catalogued features are Local Memory Store, SQLite Backend, and Agent Memory. It exposes integrations via an MCP server.
Latest indexed changes and source events
llm-memory-store verified by the PulseGate indexer
Other apps tracked under the same category.
