mempalace

MemPalace gives your AI assistant a long-term memory you actually own. It stores conversations and documents verbatim, nothing summarized away, then lets the assistant pull back the exact relevant pieces with semantic search. MIT licensed, free, no API key required, organized around a memory-palace metaphor: wings for people and projects, rooms for topics, drawers holding the original content.

It started life strictly local, and that's still the default: a Python install, a pluggable vector backend (ChromaDB by default; Qdrant, pgvector, Milvus, and SQLite all work), and an MCP server with auto-save hooks for Claude Code. It has since grown past one machine. Recent releases added a team server with TLS and authentication, an HTTP transport for the MCP server, and a coordination layer that lets agents on different machines hand work to each other.

Solo developers who want their assistant to remember context across sessions without shipping every conversation to a vendor: this is one of the strongest local options going. Small teams can now share one memory server instead of syncing folders. The closest comparison, supermemory, leans on a hosted API; MemPalace's pitch is that everything stays yours.

The catch is pace. It ships releases constantly, and the feature set moves month to month. Pin your version if you depend on it.