HyperMarrow runs on your own machine — the client starts it, so there is no endpoint to ping. 51 installs a week from npm.
Local-first long-term memory for AI coding agents. Stored on your own machine.
Today is the operative word: we check HyperMarrow 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 hypermarrow -- npx -y @qianshitech/hypermarrow-mcp
{
"mcpServers": {
"hypermarrow": {
"command": "npx",
"args": [
"-y",
"@qianshitech/hypermarrow-mcp"
]
}
}
}
[mcp_servers.hypermarrow]
command = "npx"
args = ["-y", "@qianshitech/hypermarrow-mcp"]
{
"mcpServers": {
"hypermarrow": {
"command": "npx",
"args": [
"-y",
"@qianshitech/hypermarrow-mcp"
]
}
}
}
{
"servers": {
"hypermarrow": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@qianshitech/hypermarrow-mcp"
]
}
}
}
Local-first, governable long-term memory for AI coding agents
Long-term memory for AI coding agents, stored as a tree of plain local files.
One shared, durable memory for your AI coding agents — local-first, zero-dependency.
Persistent memory for AI coding agents. #1 on LongMemEval. Local-first.
Shared memory + orchestration for your coding agents. Local-first MCP, vector RAG.
Local long-term memory shared by all your AI agents, kept word for word on your own PC.
Local-first, cross-harness memory for AI coding agents.
Local long-term memory shared by all your AI agents, kept word for word on your own PC.
Answers built from our own checks of this server.