0Latency Memory

io.github.jghiglia2380v1.0.0Updated Sep 23, 2026

Persistent memory layer for AI agents. Sub-100ms recall, semantic search, knowledge graphs.

Installation

In SourceWeft

  1. Open 0Latency Memory in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via SSE. Remote servers run from the web runtime once configured in a workspace.

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "0latency": {
      "type": "sse",
      "url": "https://mcp.0latency.ai/mcp?key={api_key}"
    }
  }
}

Tools

0
Tool metadata has not been indexed yet.

Version history

1
  1. v1.0.0LatestSep 16, 2026