Repomemory runs on your own machine — the client starts it, so there is no endpoint to ping. 85 installs a week from npm. Last commit 3 Apr 2026.
Persistent memory for AI coding agents. Hybrid search, auto-session capture, context routing.
Today is the operative word: we check Repomemory 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 repomemory -- npx -y repomemory
{
"mcpServers": {
"repomemory": {
"args": [
"-y",
"repomemory"
],
"command": "npx"
}
}
}
[mcp_servers.repomemory]
command = "npx"
args = ["-y", "repomemory"]
{
"mcpServers": {
"repomemory": {
"args": [
"-y",
"repomemory"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"repomemory": {
"args": [
"-y",
"repomemory"
],
"command": "npx"
}
}
}
Persistent memory for Claude Code. Search, recall, and re-inject context from any session.
Persistent memory for Claude Code. Search, recall, and re-inject context from any session.
Persistent knowledge memory for AI agents. Hybrid search, code graph, pgvector.
Cross-session memory for Claude Code — context capture, semantic search, recall
Persistent memory for Claude Code — offline, single-file, hybrid search.
Efficient context management: code search, evidence packs, and memory for coding agents.
Persistent memory for AI coding agents — past bugs, decisions, and your corrections, in your repo.
Operational memory for AI agents: code graph, session memory & guardrails. No context rot.
Answers built from our own checks of this server.