Epiphany runs on your own machine — the client starts it, so there is no endpoint to ping. 40 installs a week from npm. Last commit 2 Aug 2026.
One private, local memory your AI tools share. Cross-model, on-device, never lose a session.
Today is the operative word: we check Epiphany every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
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 epiphany -- npx -y epiphany-mcp
{
"mcpServers": {
"epiphany": {
"args": [
"-y",
"epiphany-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.epiphany]
command = "npx"
args = ["-y", "epiphany-mcp"]
{
"mcpServers": {
"epiphany": {
"args": [
"-y",
"epiphany-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"epiphany": {
"args": [
"-y",
"epiphany-mcp"
],
"command": "npx"
}
}
}
An MCP memory server. One memory your agents share — across models, devices and apps.
Cross-model memory for people and teams: one memory every AI you use loads at session start.
Cross-session, cross-device memory for your agent: remember and recall notes. No key to start.
AI memory layer — one shared, persistent memory across every AI tool you connect.
AI that remembers. Local-first cross-session, cross-project long-term memory for coding tools.
Cross-session memory and hybrid RAG over your notes and docs. Local-first, with cited answers.
Private on-device memory & retrieval for AI assistants — offline vector + lexical search.
Your product team's shared strategic memory — an MCP server your AI tools reason over.
Answers built from our own checks of this server.