Neurakeep runs on your own machine — the client starts it, so there is no endpoint to ping. 53 installs a week from npm. Last commit 23 Aug 2026.
Local-first, source-cited memory for AI agents with proposal review, failure memory, and MCP tools.
We read the source, 12 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.
const child = spawnSync(process.execPath, [cliPath, "text", sourcePath, "--format", "text"], {
return (db.prepare(`SELECT COUNT(*) AS count FROM ${table}`).get() as { count: number }).count;
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 neurakeep -- npx -y neurakeep
{
"mcpServers": {
"neurakeep": {
"args": [
"-y",
"neurakeep"
],
"command": "npx"
}
}
}
[mcp_servers.neurakeep]
command = "npx"
args = ["-y", "neurakeep"]
{
"mcpServers": {
"neurakeep": {
"args": [
"-y",
"neurakeep"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"neurakeep": {
"args": [
"-y",
"neurakeep"
],
"command": "npx"
}
}
}
SEAM: local-first memory runtime for AI agents, with retrieval and glassbox provenance over MCP.
Local-first memory for AI agents: ground truths, failure firewall, negotiated recall over MCP.
Long-term memory for AI agents: local-first PKM with provenance and hybrid search.
Local MCP server for Recite receipt processing with ledger and memory tools.
Local-first graph memory for AI assistants with SQLite, semantic search, and MCP tools.
Persistent memory, coordination, and learning for AI agents. Local-first, 25 MCP tools.
Local-first memory for AI agents that reaches backward to find a failure's root cause.
Local-first memory system for AI agents with hybrid search and graph reasoning
Answers built from our own checks of this server.