mcpField
0
0Latency

0Latency

Remote
0latency.aiAI & Agents2Updated 9w ago
RepositoryVisit website

About 0Latency

0Latency is a multi-tenant memory API for AI agents, with an MCP server package for connecting agents to persistent memory. It supports semantic recall, automatic deduplication, and knowledge graphs.

Key features

  1. 01Store memories across sessions
  2. 02Recall memories with semantic search
  3. 03Automatically deduplicate similar memories
  4. 04Support knowledge graphs
  5. 05Isolate storage by tenant

Use cases

  1. 01Keep agent context between sessions
  2. 02Recall relevant memories by meaning
  3. 03Reduce duplicate stored memories

MCP support

The @0latency/mcp-server package exposes 0Latency's memory API to MCP clients. It uses an API key supplied through the ZERO_LATENCY_API_KEY environment variable.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://mcp.0latency.ai/mcp?key=zl_live_YOUR_API_KEY
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

0Latency

Long-term memory for AI agents that actually works.

Quick Start

npm install @0latency/mcp-server

Add to your MCP settings:

{
  "mcpServers": {
    "0latency": {
      "command": "npx",
      "args": ["-y", "@0latency/mcp-server"],
      "env": {
        "ZERO_LATENCY_API_KEY": "your-api-key"
      }
    }
  }
}

Get your API key at 0latency.ai

Documentation

What is 0Latency?

0Latency is a multi-tenant memory API for AI agents. Extract, store, and recall contextual memories with semantic search, automatic deduplication, and sub-100ms retrieval.

Features

  • 🧠 Long-term memory storage across sessions
  • 🔍 Semantic search with vector embeddings
  • ⚡ Sub-100ms cached query performance
  • 🔄 Automatic deduplication (>92% similarity)
  • 📊 Knowledge graph support
  • 🔐 Tenant-isolated, secure storage

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.