Vector Memory runs on your own machine — the client starts it, so there is no endpoint to ping. 149 installs a week from pypi.
Semantic document memory using Redis vector store. Save and recall files with natural language.
Nothing serious here today
Today is the operative word: we check Vector Memory every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Connect this server
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add vector-memory -- uvx mcp-server-vector-memory{
"mcpServers": {
"vector-memory": {
"command": "uvx",
"args": [
"mcp-server-vector-memory"
]
}
}
}[mcp_servers.vector-memory]
command = "uvx"
args = ["mcp-server-vector-memory"]{
"mcpServers": {
"vector-memory": {
"command": "uvx",
"args": [
"mcp-server-vector-memory"
]
}
}
}{
"servers": {
"vector-memory": {
"type": "stdio",
"command": "uvx",
"args": [
"mcp-server-vector-memory"
]
}
}
}Alternatives to Vector Memory
same job, measured the same wayLocal FAISS vector database for RAG with document ingestion, semantic search, and MCP prompts.
Persistent semantic memory for AI agents using local ChromaDB vector search. No cloud required.
Shared cross-LLM long-term memory over MCP: semantic recall, sessions, and media (pgvector).
Bilingual dual memory with SSC for AI agents. Semantic search, embeddings, profiles.
Local vector and raster editing engine for agents: layered documents, saved sessions and exports.
Portable agent memory anchored on Solana. Local SQLite + vector recall, open export.
Self-hosted AI workspace: semantic RAG document search, long-term memory, and AI chat via MCP.
RAG memory for LLM agents over Garnet Vector Sets: store text as embeddings, recall by meaning.
Vector Memory — questions
Answers built from our own checks of this server.