Audrey runs on your own machine — the client starts it, so there is no endpoint to ping. 551 installs a week from npm. Last commit 29 Oct 2026.
Local-first biological memory for coding agents: recall, consolidation, and pre-action Guard checks.
We read the source, 3 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.
const child = spawn(invocation.command, [...invocation.argsPrefix, 'app-server', '--stdio'], {
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 audrey -- npx -y audrey
{
"mcpServers": {
"audrey": {
"command": "npx",
"args": [
"-y",
"audrey"
]
}
}
}
[mcp_servers.audrey]
command = "npx"
args = ["-y", "audrey"]
{
"mcpServers": {
"audrey": {
"command": "npx",
"args": [
"-y",
"audrey"
]
}
}
}
{
"servers": {
"audrey": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"audrey"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
AUDREY_DATA_DIR (Directory for the SQLite memory store (defaults to ~/.audrey/data)), AUDREY_AGENT (Logical memory owner used for scoped operations (defaults to local-agent)), AUDREY_EMBEDDING_PROVIDER (local (default, on-device model), openai, gemini, or mock), AUDREY_LLM_PROVIDER (Optional reflection/consolidation model: anthropic, openai, chatgpt, or mock; unset keeps everything local), AUDREY_ENABLE_ADMIN_TOOLS (Set to 1 to expose the export, import, forget, and promote tools).
Local-first project memory and mistake-prevention guardrails for AI coding agents.
Local-first governed MCP memory backend for coding agents.
Local-first governed MCP memory backend for coding agents.
Session memory for coding agents: local-first recall, drift detection, on-device inference.
Persistent, local-first memory for AI coding agents. Remember, recall and forget across sessions.
Local-first, persistent memory for AI coding agents — remember, recall, forget, and list, over MCP.
Local-first control plane for coding agents: routing, reservations, and guardrails.
Local-first persistent memory for coding agents and MCP clients.
Answers built from our own checks of this server.