thought-mcp is an open-source toolkit that implements a local Model Context Protocol (MCP) memory server with bi-temporal graph, vector, and temporal layers. It enables AI agents to store, retrieve, and consolidate structured memory for advanced reasoning and context management.
In the AI & ML space, thought-mcp takes a focused approach. It focuses on providing AI agents with a local, bi-temporal graph and vector memory server for advanced context and retrieval. It is built as an open-source project for ai agent developers. thought-mcp is open source under the MIT license. thought-mcp is available on the web and the command line, and it can be self-hosted.
Behind thought-mcp is RNBBarrett, and the product first shipped in 2026. Development happens publicly on GitHub with 19 commits in the last 90 days. PulseGate's similarity index finds few close equivalents — thought-mcp occupies a relatively distinct niche. Key capabilities include bi-temporal graph memory, vector storage, and query router. It exposes integrations via an MCP server.
Latest indexed changes and source events
Other apps tracked under the same category.
