Longmem runs on your own machine — the client starts it, so there is no endpoint to ping. 38 installs a week from pypi. Last commit 17 Apr 2026.
Persistent cross-project memory for Cursor and Claude Code using local semantic search.
Today is the operative word: we check Longmem every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
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 longmem -- uvx longmem
{
"mcpServers": {
"longmem": {
"command": "uvx",
"args": [
"longmem"
]
}
}
}
[mcp_servers.longmem]
command = "uvx"
args = ["longmem"]
{
"mcpServers": {
"longmem": {
"command": "uvx",
"args": [
"longmem"
]
}
}
}
{
"servers": {
"longmem": {
"type": "stdio",
"command": "uvx",
"args": [
"longmem"
]
}
}
}
Semantic codebase search + persistent working memory for AI code editors. Local, no API key.
Persistent memory for Claude Code. Search, recall, and re-inject context from any session.
Persistent memory for Claude Code and Codex. Search and re-inject context from any session.
Persistent memory MCP server for Claude Code, Cursor, and GitHub Copilot.
Persistent memory for AI agents: one brain shared across Claude, Cursor, Codex and more.
Persistent memory for Claude Code — offline, single-file, hybrid search.
Cross-session memory for Claude Code — context capture, semantic search, recall
Persistent session memory for Claude Code. Local SQLite, no LLMs, no network.
Answers built from our own checks of this server.