Dawnmere runs on your own machine — the client starts it, so there is no endpoint to ping. 321 installs a week from npm. Last commit 10 Nov 2026.
One local memory shared by Claude Code, Codex and Cursor. Connects to Dawnmere on your Mac.
Today is the operative word: we check Dawnmere 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 dawnmere-connector -- npx -y dawnmere-connector
{
"mcpServers": {
"dawnmere-connector": {
"command": "npx",
"args": [
"-y",
"dawnmere-connector"
]
}
}
}
[mcp_servers.dawnmere-connector]
command = "npx"
args = ["-y", "dawnmere-connector"]
{
"mcpServers": {
"dawnmere-connector": {
"command": "npx",
"args": [
"-y",
"dawnmere-connector"
]
}
}
}
{
"servers": {
"dawnmere-connector": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"dawnmere-connector"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
LFLABS_MEMORY_CLIENT (A name for this app (cursor, codex, windsurf...). Dawnmere shows it and uses it for what this app may see).
One memory for you and your AI agents, shared by ChatGPT, Claude, Gemini, Grok, Codex and Cursor.
One shared, versioned memory for Claude Code, Cursor, Codex and every MCP agent. Local and offline.
Persistent memory for AI agents: one brain shared across Claude, Cursor, Codex and more.
Wontopos (WOS) long-term memory (beta) - one memory across Claude Code, Cursor, and your agents.
Shared memory and delegation for Codex, Cursor, Claude Code, and OpenCode.
Local Markdown task memory shared by Claude Code and Codex over stdio MCP.
Connect Claude, Cursor, Codex, and other MCP clients to manage your Cavuno job board.
Your AI apps as one team: hand work to Codex or Claude Code on your Mac, with a shared logbook.
Answers built from our own checks of this server.