Total Agent Memory runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 15 Sep 2026.
Persistent local memory for coding agents: temporal knowledge graph, procedural and episodic recall
We read the source, 18 h ago · rules 3dff92dd89df
Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.
result = subprocess.run(
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.
raise SystemExit(subprocess.call(argv))
return {"type": "command", "command": os.path.join(launcher_dir, name)}
url = f"https://api.telegram.org/bot{token}/sendMessage"
raw_mb = sum(f.stat().st_size for f in (MEMORY_DIR / "raw").iterdir() if f.is_file()) / 1048576
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
Code changes quietly between releases, and nobody reads the diff of a dependency. We do, on every release — watch Total Agent Memory and you get told the day something new turns up.
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 total-agent-memory -- uvx total-agent-memory
{
"mcpServers": {
"total-agent-memory": {
"args": [
"total-agent-memory"
],
"command": "uvx"
}
}
}
[mcp_servers.total-agent-memory]
command = "uvx"
args = ["total-agent-memory"]
{
"mcpServers": {
"total-agent-memory": {
"args": [
"total-agent-memory"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"total-agent-memory": {
"args": [
"total-agent-memory"
],
"command": "uvx"
}
}
}
Persistent memory for AI agents. Remember, recall, and explore a shared knowledge graph.
Persistent long-term memory for AI agents: semantic search, knowledge graph, and task canvas.
Local-first knowledge engine for AI agents: memory, graph, and recall over MCP.
Local memory engine for AI agents with knowledge graphs, forgetting, and semantic recall
Persistent code knowledge graph + 9 composite MCP tools for AI coding agents.
Local-first memory and knowledge graph for coding agents. Compact retrieval, no network.
Persistent knowledge-graph memory for AI agents, with local semantic search. No API keys.
Persistent memory for AI thinking partnerships: hybrid search and a temporal knowledge graph.
Answers built from our own checks of this server.