No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by ZenSystemAI · MCP Server · ★ 60
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is Zengram safe to install? View the security audit →
Zengram Shared memory for multi-agent AI systems. Quick Start • How It Works • Benchmarks • Adapters • API Docs • Config <img src=".github/hero.jpg" alt="Zengram — shared memory for multi-agent AI
| Stars | 60 |
| Forks | 10 |
| Language | JavaScript |
| Category | MCP Server |
| License | MIT |
| Quality Score | 63.3646054754338/100 |
| Open Issues | 2 |
| Last Updated | 2026-09-29 |
| Created | 2026-03-10 |
| Platforms | claude-code, codex, gemini, mcp, node |
| Est. Tokens | ~15k |
These tools work well together with Zengram for enhanced workflows:
Looking for a Zengram alternative? If you're comparing Zengram with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
MCP server giving AI agents full access to Julia's runtime via a live Gate — code execution, introspection, de
Better 'AskUserQuestion' - A lightweight MCP server/OpenCode plugin/Agent Skills + CLI tool that allows your L
DeepContext is an MCP server that adds symbol-aware semantic search to Claude Code, Codex CLI, and other agent
A collection of AI agent skills for Clawdbot, Claude Code, Codex
📜 An MCP server for conversation history search and retrieval in Claude Code
Transform your codebase into an intelligent knowledge base for AI-powered development with Cursor IDE, Google
Explore other popular mcp server tools:
Zengram is A Multi Agent Memory MCP That Connect Agents Across Systems and Machines. It is categorized as a MCP Server with 60 GitHub stars.
Zengram is primarily written in JavaScript. It covers topics such as claude, claude-ai, claude-code.
You can find installation instructions and usage details in the Zengram GitHub repository at github.com/ZenSystemAI/Zengram. The project has 60 stars and 10 forks, indicating an active community.
Zengram is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to Zengram on Agent Skills Hub include Kaimon.jl, ask-user-questions-mcp, deepcontext-mcp. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: