Recall — persistent memory for agents is answering right now. Last checked 4 min ago. It exposes 5 tools.
Persistent memory for AI agents. Free, no LLM, no SDK. Open Worker you can self-host in 2 commands.
Everything else answered, so this is steady rather than shaky. We check every 15 minutes, which is how a one-off gets told apart from the start of a pattern, and how you hear about the next one within the hour instead of from your users.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 4 min ago.
claude mcp add memory --transport http 'https://recall.notdown-app.workers.dev/mcp/{key}'
https://recall.notdown-app.workers.dev/mcp/{key}
[mcp_servers.memory]
url = "https://recall.notdown-app.workers.dev/mcp/{key}"
{
"mcpServers": {
"memory": {
"url": "https://recall.notdown-app.workers.dev/mcp/{key}"
}
}
}
{
"servers": {
"memory": {
"type": "http",
"url": "https://recall.notdown-app.workers.dev/mcp/{key}"
}
}
}
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
memory_forget
memory_list
memory_recall
memory_save
memory_search
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://recall.notdown-app.workers.dev/mcp/{key} | streamable-http | answering | 266 ms | 4 min ago |
Local-first, persistent memory for AI coding agents — remember, recall, forget, and list, over MCP.
Persistent memory for AI agents — log and recall conversation context over MCP.
Offline persistent memory for AI coding agents — 35 tools, 80% fewer calls, no LLM
Persistent memory for AI agents. Memories decay with time and strengthen on recall.
Persistent memory for AI agents — local JSON, zero config, no server required.
Persistent memory for AI agents. Search, store, and recall across sessions.
Persistent memory for AI agents: local-first MCP server, zero-config. No cloud, no API keys.
Local-first persistent memory MCP server for AI coding agents.
Answers built from our own checks of this server.