Amber is answering right now. Last checked 1 min ago. Last commit 2 Nov 2026.
Long-term memory for AI assistants: permanent, portable across clients, searchable and exportable.
Today is the operative word: we check Amber every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 1 min ago.
claude mcp add amber --transport http https://mcp.ambermem.com
https://mcp.ambermem.com
[mcp_servers.amber]
url = "https://mcp.ambermem.com"
{
"mcpServers": {
"amber": {
"url": "https://mcp.ambermem.com"
}
}
}
{
"servers": {
"amber": {
"type": "http",
"url": "https://mcp.ambermem.com"
}
}
}
This endpoint answered with an authorization challenge. The server is running, and it signs you in through your browser: there is no API key to paste.
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://mcp.ambermem.com | streamable-http | sign-in | 269 ms | 1 min ago |
Persistent, verbatim, searchable memory for AI assistants — one memory across every MCP client.
Persistent personal memory for AI assistants — save, search, and recall across every MCP client.
Persistent memory for AI assistants. Store, search, and recall across sessions.
Long-term memory for AI agents — your Obsidian vault as searchable persistent memory.
Persistent searchable memory for AI agents — save/get/search across sessions, tags.
Persistent memory for AI agents: add, search, update, and delete long-term memories.
Free web search and long-term memory for AI assistants. No API keys; data stays local.
Long-term memory for AI assistants. Isolated per-user storage, recall across conversations.
Answers built from our own checks of this server.