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 slow-stack · MCP Server · ★ 138
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is mneme safe to install? View the security audit →
dsh-mneme 🌏 简体中文 · <a href="#e
| Stars | 138 |
| Forks | 20 |
| Language | JavaScript |
| Category | MCP Server |
| License | MIT |
| Quality Score | 65.2051118314618/100 |
| Open Issues | 15 |
| Last Updated | 2026-10-03 |
| Created | 2026-08-13 |
| Platforms | claude-code, codex, mcp, node |
| Est. Tokens | ~17k |
These tools work well together with mneme for enhanced workflows:
Looking for a mneme alternative? If you're comparing mneme 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.
Local-first persistent agentic memory powered by Recursive Memory Harness (RMH). Open source must win.
Biologically-inspired persistent memory engine for Claude Code. 26 cognitive subsystems, Hopfield networks, pr
Structural memory for AI coding agents. Bi-temporal graph, MCP-native, zero LLM calls. Cursor · Claude Code ·
Persistent memory for AI coding agents
Cross-platform persistent memory MCP for Codex, Gemini CLI, Claude Code, and other local MCP hosts. 36 cited n
Outcome-based persistent memory MCP server for Claude Code and OpenCode. Good advice promoted, bad advice demo
Explore other popular mcp server tools:
mneme is 🧠 The memory that dreams — cross-session memory for DeepSeek Harness. Offline & private, auto-consolidates in its sleep (autoDream), visualized in a memory panel.. It is categorized as a MCP Server with 138 GitHub stars.
mneme is primarily written in JavaScript. It covers topics such as agent-memory, agent-memory-system, autodream.
You can find installation instructions and usage details in the mneme GitHub repository at github.com/slow-stack/mneme. The project has 138 stars and 20 forks, indicating an active community.
mneme is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to mneme on Agent Skills Hub include Ori-Mnemos, Zikkaron, memtrace-public. 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: