Peon Mem runs on your own machine — the client starts it, so there is no endpoint to ping. 531 installs a week from npm. Last commit 15 Sep 2026.
Local-first memory brain for AI coding agents: hooks capture sessions, beliefs injected per prompt.
Today is the operative word: we check Peon Mem 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 peon-mem -- npx -y peon-mem
{
"mcpServers": {
"peon-mem": {
"args": [
"-y",
"peon-mem"
],
"command": "npx"
}
}
}
[mcp_servers.peon-mem]
command = "npx"
args = ["-y", "peon-mem"]
{
"mcpServers": {
"peon-mem": {
"args": [
"-y",
"peon-mem"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"peon-mem": {
"args": [
"-y",
"peon-mem"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
PEON_DAEMON_URL (Peon daemon address).
The author declared them in the registry entry; get the values from the project itself.
Local-first persistent memory for AI coding agents.
Local-first, cross-harness memory for AI coding agents.
Decision memory for AI coding agents: captures decisions once, briefs every agent before it acts.
Local-first project memory and mistake-prevention guardrails for AI coding agents.
Session memory for coding agents: local-first recall, drift detection, on-device inference.
Persistent memory for AI coding agents. #1 on LongMemEval. Local-first.
Local-first memory and session continuity for AI coding agents over MCP. No cloud, no telemetry.
Persistent memory for AI coding agents. Hybrid search, auto-session capture, context routing.
Answers built from our own checks of this server.