Agentage Memory is answering right now. Last checked moments ago.
One memory, every AI. A shared, user-owned markdown memory your AI clients read and write over MCP.
Nothing serious here today
Today is the operative word: we check Agentage Memory every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Connect this server
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 0 min ago.
claude mcp add memory --transport http https://memory.agentage.io/mcp{
"mcpServers": {
"memory": {
"url": "https://memory.agentage.io/mcp"
}
}
}[mcp_servers.memory]
url = "https://memory.agentage.io/mcp"{
"mcpServers": {
"memory": {
"url": "https://memory.agentage.io/mcp"
}
}
}{
"mcpServers": {
"memory": {
"url": "https://memory.agentage.io/mcp"
}
}
}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.
Endpoints
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://memory.agentage.io/mcp | streamable-http | sign-in | 167 ms | 0 min ago |
Alternatives to Agentage Memory
same job, measured the same wayA shared team wiki your coding agents read and write — across every repo and every MCP client.
Shared memory for all your AI agents, your whole team and every MCP client — save, search, recall.
One shared memory for every AI you use, in plain Markdown files you own.
Personal AI memory layer on your own computer. Read/write durable memory across MCP clients.
Shared memory for AI agents, as a graph in your own Postgres. Writes never call an LLM.
Cross-vendor AI memory over MCP. One semantic store, readable and writeable from every MCP client.
Read and write your team's shared, AI-readable wiki from any MCP client.
A committed markdown dev log and task graph that agents read and write over MCP.
Agentage Memory — questions
Answers built from our own checks of this server.