Deja Vu runs on your own machine — the client starts it, so there is no endpoint to ping. 2 686 installs a week from npm. Last commit 2 Nov 2026.
deja-vu: local memory over the session histories of forty-three coding agents.
What the code does
We read the source, 23 h 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(resolveDeja(), ["mcp"], { windowsHide: true, stdio: "inherit" })
if _, err := os.Stat(filepath.Join(dir, zedServerID)); err == nil {
return text[:block.valueOpen+1] + insert + text[block.valueOpen+1:], nil
done = subprocess.run(
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
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.
Connect this server
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 deja-vu -- npx -y @vshulcz/deja-vu{
"mcpServers": {
"deja-vu": {
"command": "npx",
"args": [
"-y",
"@vshulcz/deja-vu"
]
}
}
}[mcp_servers.deja-vu]
command = "npx"
args = ["-y", "@vshulcz/deja-vu"]{
"mcpServers": {
"deja-vu": {
"command": "npx",
"args": [
"-y",
"@vshulcz/deja-vu"
]
}
}
}{
"servers": {
"deja-vu": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@vshulcz/deja-vu"
]
}
}
}Alternatives to Deja Vu
same job, measured the same wayLocal Git-history memory for coding agents: reverts, suppressions, hotspots, and annotations.
Cross-session memory for AI coding agents via six tools; local-first SQLite store.
Long-term memory for AI coding agents, stored as a tree of plain local files.
Memory for coding agents: the decisions, the dead ends, and where the last session stopped.
Session memory for coding agents: local-first recall, drift detection, on-device inference.
Shared memory MCP server for AI coding agents — local by default, team-shared via threadctx.dev.
Local-first persistent memory MCP server for AI coding agents.
Local-first memory for coding agents; stores decisions, bugs, and context across sessions.
Deja Vu — questions
Answers built from our own checks of this server.