m3-memory is an open-source memory framework for AI agents, offering local-first storage, hybrid and vector search, and compatibility with the Model Context Protocol (MCP). It supports both offline and cloud operation, making it suitable for advanced AI agent development.
m3-memory sits in PulseGate's RAG, search & retrieval category. It enables AI agents to store and retrieve long-term memory efficiently, supporting both local and cloud modes. It is built as an open-source project for AI agent developers. m3-memory is open source under the Apache-2.0 license. The product ships for the command line.
It is developed by skynetcmd, and the product first shipped in 2026. Development happens publicly on GitHub with 14 stars and 747 commits in the last 90 days. PulseGate's similarity index finds few close equivalents — m3-memory occupies a relatively distinct niche. Key capabilities include local memory storage, hybrid search, and vector search. It exposes integrations via an MCP server.
Latest indexed changes and source events
Other apps tracked under the same category.
