mempalace

Why we included this project

MemPalace keeps a long-running assistant's context alive by storing the actual conversation text and retrieving it with semantic search when a new session starts. It deliberately does not summarize or paraphrase, so the original wording stays intact, and the index is organized into scoped sections for people, projects, and topics rather than one flat pile. The storage backend is pluggable (ChromaDB by default) and it speaks the Model Context Protocol, so it can serve as a memory server for tools like Claude Code, with a Docker image for easy deployment. Everything stays on your machine unless you opt in, which makes it a good fit for teams that want durable memory without paying per API call or shipping chat logs to a cloud service.