ZenSystemAI/Zengram
A Multi Agent Memory MCP That Connect Agents Across Systems and Machines
Platform-specific configuration:
{
"mcpServers": {
"Zengram": {
"command": "npx",
"args": [
"-y",
"Zengram"
]
}
}
}Add the config above to .claude/settings.json under the mcpServers key.
<p align="center"> <h1 align="center">Zengram</h1> <p align="center"> <strong>Shared memory for multi-agent AI systems.</strong> </p> <p align="center"> <a href="#quick-start">Quick Start</a> • <a href="#how-it-works">How It Works</a> • <a href="#benchmarks">Benchmarks</a> • <a href="#adapters--sdks">Adapters</a> • <a href="docs/api-reference.md">API Docs</a> • <a href="docs/configuration.md">Config</a> </p> <p align="center"> <a href="https://github.com/ZenSystemAI/zengram/actions/workflows/ci.yml"></a> <a href="https://www.npmjs.com/package/@zensystemai/zengram-mcp"></a> <a href="https://github.com/ZenSystemAI/zengram/stargazers"></a> </p> </p>
<p align="center"> </p>
Store a fact from Claude Code on your laptop, recall it from an autonomous agent on your server, get a briefing from n8n — all through the same memory system. Born from a production setup where nothing existed that let multiple AI agents share memory across separate machines.
---
<p align="center"> </p>
You run multiple AI agents — Claude Code for deve
Loading reviews...