Shodh Memory runs on your own machine — the client starts it, so there is no endpoint to ping. 82 installs a week from npm. Last commit 13 Sep 2026.
Cognitive memory for AI agents — semantic search, Hebbian learning, knowledge graphs.
We read the source, 19 h ago · rules 3dff92dd89df
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.
postinstall: node scripts/postinstall.cjs
runningHelper = spawn(windowsHelper.command, [
self._server_process = subprocess.Popen(
zenoh::sample::SampleKind::Delete => {
info!(robot_id = %robot_id, "Fleet peer left");
const binaryPath = path.join(binDir, fallbackName);
"!pip install shodh-memory -q\n",
for (const [key, value] of Object.entries(process.env)) {
const PREFIXES: &[&str] = &["id_rsa", "id_ed25519", "id_ecdsa", "id_dsa", ".env"];
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
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.
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 shodh-memory -- npx -y @shodh/memory-mcp
{
"mcpServers": {
"shodh-memory": {
"args": [
"-y",
"@shodh/memory-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.shodh-memory]
command = "npx"
args = ["-y", "@shodh/memory-mcp"]
{
"mcpServers": {
"shodh-memory": {
"args": [
"-y",
"@shodh/memory-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"shodh-memory": {
"args": [
"-y",
"@shodh/memory-mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
SHODH_API_URL (URL of the shodh-memory backend server), SHODH_API_KEY (API key for authentication), SHODH_USER_ID (User ID for memory isolation).
The author declared them in the registry entry; get the values from the project itself.
Cross-session memory for AI agents - knowledge graph, scoring, semantic search
Event-sourced knowledge graph memory for AI coding agents with semantic search
Cognitive memory for AI agents — semantic recall, knowledge graph, and contradiction detection
Semantic memory for AI agents with hybrid search, knowledge graph, and consolidation
Persistent long-term memory for AI agents: semantic search, knowledge graph, and task canvas.
Persistent knowledge-graph memory for AI agents, with local semantic search. No API keys.
Local memory engine for AI agents with knowledge graphs, forgetting, and semantic recall
High-performance knowledge graph MCP server for AI coding agents with semantic search.
Answers built from our own checks of this server.