Nan Forget runs on your own machine — the client starts it, so there is no endpoint to ping. 74 installs a week from npm. Last commit 6 Apr 2026.
AI that remembers. Local-first cross-session, cross-project long-term memory for coding tools.
We read the source, 21 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 output = execSync(cmd, { encoding: 'utf-8', stdio: ['pipe', 'pipe', 'pipe'] });
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 nan-forget -- npx -y nan-forget
{
"mcpServers": {
"nan-forget": {
"args": [
"-y",
"nan-forget"
],
"command": "npx"
}
}
}
[mcp_servers.nan-forget]
command = "npx"
args = ["-y", "nan-forget"]
{
"mcpServers": {
"nan-forget": {
"args": [
"-y",
"nan-forget"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"nan-forget": {
"args": [
"-y",
"nan-forget"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
OPENAI_API_KEY (OpenAI API key for embeddings. If not set, falls back to local Ollama.), NAN_FORGET_EMBEDDING_PROVIDER (Embedding provider: openai or ollama), NAN_FORGET_USER_ID (User identifier for multi-user setups), NAN_FORGET_PROJECT_ROOT (Project root used for local memory file sync and cleanup).
The author declared them in the registry entry; get the values from the project itself.
Persistent memory for AI coding tools via MCP. Remembers across sessions and machines.
Local-first, cross-harness memory for AI coding agents.
Local-first, governable long-term memory for AI coding agents
Local-first AI context and memory server for cross-tool coding continuity.
Deterministic context selection for AI coding agents. Local memory that compounds across sessions.
Local-first project memory and mistake-prevention guardrails for AI coding agents.
Persistent memory for AI coding agents. #1 on LongMemEval. Local-first.
Local-first memory and session continuity for AI coding agents over MCP. No cloud, no telemetry.
Answers built from our own checks of this server.