server-noonien runs on your own machine — the client starts it, so there is no endpoint to ping. 357 installs a week from npm. Last commit 29 Oct 2026.
Shared, serverless, conflict-free knowledge-graph memory for AI agents
Today is the operative word: we check server-noonien 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 server-noonien -- npx -y server-noonien
{
"mcpServers": {
"server-noonien": {
"command": "npx",
"args": [
"-y",
"server-noonien"
]
}
}
}
[mcp_servers.server-noonien]
command = "npx"
args = ["-y", "server-noonien"]
{
"mcpServers": {
"server-noonien": {
"command": "npx",
"args": [
"-y",
"server-noonien"
]
}
}
}
{
"servers": {
"server-noonien": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"server-noonien"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
NOONIEN_DIR (Directory holding this machine's shards (default ~/.noonien)), NOONIEN_NODE_ID (This node's shard name (default the hostname). Must be unique per machine).
Token-lean memory for AI agents: a knowledge graph searched cheaply. Drop-in for server-memory.
Knowledge-graph memory server for AI tools via MCP
Local knowledge graph memory MCP server for AI assistants.
Persistent memory for AI agents. Remember, recall, and explore a shared knowledge graph.
Cross-session memory for AI agents - knowledge graph, scoring, semantic search
Graph-native memory for AI agents: a knowledge graph built from conversation, via MCP.
Shared long-term memory for AI agents: save and recall context as a searchable knowledge graph.
Event-sourced knowledge graph memory for AI coding agents with semantic search
Answers built from our own checks of this server.