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 mindscale-noah · Codex Skill · ★ 970
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is MindMemOS safe to install? View the security audit →
简体中文 │ &
| Stars | 970 |
| Forks | 95 |
| Language | Python |
| Category | Codex Skill |
| Quality Score | 53.4292403603758/100 |
| Last Updated | 2026-09-01 |
| Created | 2026-06-23 |
| Platforms | python |
| Est. Tokens | ~19k |
These tools work well together with MindMemOS for enhanced workflows:
Looking for a MindMemOS alternative? If you're comparing MindMemOS with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown a
Enhanced LanceDB memory plugin for OpenClaw — Hybrid Retrieval (Vector + BM25), Cross-Encoder Rerank, Multi-Sc
Enhanced LanceDB memory plugin for OpenClaw — Hybrid Retrieval (Vector + BM25), Cross-Encoder Rerank, Multi-Sc
Nuwax Agent OS - An enterprise-grade AI Agent Development and Operation Platform - Providing a complete soluti
Deepseek Harness、Openclaw知识图谱记忆插件。2026年4月受邀发布在清华大学讨论会。Knowledge Graph + Memory；Knowledge Graph Context Engine
A full-stack AI Red Teaming platform securing AI ecosystems via OpenClaw Security Scan, Agent Scan, Skills Sca
Explore other popular codex skill tools:
MindMemOS is an open-source codex skill by mindscale-noah with 970 GitHub stars.
MindMemOS is primarily written in Python. It covers topics such as agent, agent-memory, agent-skills.
You can find installation instructions and usage details in the MindMemOS GitHub repository at github.com/mindscale-noah/MindMemOS. The project has 970 stars and 95 forks, indicating an active community.
The top alternatives to MindMemOS on Agent Skills Hub include memsearch, memory-lancedb-pro, memory-lancedb-pro. 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: