agentmem runs on your own machine — the client starts it, so there is no endpoint to ping. 97 installs a week from pypi. Last commit 17 Apr 2026.
Governed memory for coding agents. Trust lifecycle, conflict detection, health scoring.
Today is the operative word: we check agentmem 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 agentmem -- uvx quilmem
{
"mcpServers": {
"agentmem": {
"args": [
"quilmem"
],
"command": "uvx"
}
}
}
[mcp_servers.agentmem]
command = "uvx"
args = ["quilmem"]
{
"mcpServers": {
"agentmem": {
"args": [
"quilmem"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"agentmem": {
"args": [
"quilmem"
],
"command": "uvx"
}
}
}
Self-learning memory for AI coding agents with pattern detection and confidence scoring.
Local-first governed MCP memory backend for coding agents.
Local-first, governable long-term memory for AI coding agents
Authority-weighted memory graph for AI agents with conflict detection and semantic search.
Deterministic cross-branch conflict detection for AI coding agents
Persistent AI memory with semantic search, conflict detection, and ticketing.
Session memory for coding agents: local-first recall, drift detection, on-device inference.
Local adaptive memory for AI coding agents through a five-tool MCP lifecycle.
Answers built from our own checks of this server.