Memex runs on your own machine — the client starts it, so there is no endpoint to ping. 471 installs a week from npm. Last commit 8 Sep 2026.
Zettelkasten-based agent memory system with bidirectional links
What the code does
We read the source, 2 d ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
execFile(bin, [MEMRA_URL], { shell: process.platform === "win32" }, () => {});
document.getElementById('heatmap').innerHTML = html;
`\n 2. If no key exists: ssh-keygen -t ed25519 && ssh-add ~/.ssh/id_ed25519` +
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Connect this server
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 memex -- npx -y @touchskyer/memex{
"mcpServers": {
"memex": {
"command": "npx",
"args": [
"-y",
"@touchskyer/memex"
]
}
}
}[mcp_servers.memex]
command = "npx"
args = ["-y", "@touchskyer/memex"]{
"mcpServers": {
"memex": {
"command": "npx",
"args": [
"-y",
"@touchskyer/memex"
]
}
}
}{
"servers": {
"memex": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@touchskyer/memex"
]
}
}
}Optional settings from the registry entry, left out of the block above:
MEMEX_HOME (Custom data directory for memex cards (default: ~/.memex)).
Alternatives to Memex
same job, measured the same wayHosted agent memory with record-based verification, conflict detection, correction and deletion.
Bidirectional AI agent collaboration — spawn and communicate with any agent CLI
Two-layer memory for AI agents with an immune system. Zero dependencies.
Graph-based memory system for LLMs with knowledge graphs and semantic search.
Shared, persistent memory for AI assistants, built on the Zettelkasten method.
Persistent file-based memory for AI agents: inspectable, versionable, fully local.
Memory system for AI agents with semantic search. Store and recall memories with ease.
Persistent, inspectable memory for AI agents with lineage, correction, and a hosted MCP endpoint.
Memex — questions
Answers built from our own checks of this server.