server-noonien MCP server

server-noonien

Shared, serverless, conflict-free memory for AI agents — with peer-to-peer sync.

server-noonien is a drop-in replacement for the official @modelcontextprotocol/server-memory knowledge graph — the same entities, observations and relations — that converges across machines with no central server, no database and no merge conflicts.

Its headline feature is peer-to-peer sync: the nooniend daemon replicates each node's shard directly to the others, so several machines share one memory with no shared folder — only IP reachability over a VPN or a LAN.

Table of contents

• Why server-noonien
• The problem
• How server-noonien solves it
• Comparison
• The three commands
• Share across machines
• Peer to peer — nooniend (recommended)
• The daemon HTTP API
• Shared area — file and s3
• Configuration
• Shared variables
• Server variables

Why server-noonien

The problem

Agent memory today is local, and the official memory server is a single JSONL file that every mutation reads and rewrites in full. That breaks the moment you have more than one machine:

only*: two hosts each load the whole graph, mutate their own copy and write it back, so the last write silently discards the other's — and the sync tool forks the file into conflict copies instead of merging it.

• It lives on one host. Switch machine and your agent has forgotten everything.
• Sharing it over a synced folder loses writes. The server serializes mutations *in-process

are something you have to host, or they ship your memory off your machines.

• The alternatives want a server, a database or a cloud. The mainstream "shared memory" products

How server-noonien solves it

server-noonien removes the shared file and the central server at the root, and keeps the drop-in tool surface:

Shortened. The full README is on GitHub.