memX — security grade SAFE, quality 65/100

Security audit verdict: SAFE · quality 65/100

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 NeoLi00 · Claude Skill · ★ 407

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is memX safe to install? View the security audit →

About memX

English · 中文 · Architecture memX turns completed work into structured, searchable, self-maintained memory, then injects only the evidence an agent needs for the current query. It connects natively to Codex, Claude Code, and OpenClaw, and reaches any MCP-compatible client through the same local memory layer. Benchmarks Suite Scope R@3 success rate LongMemEval-S Long-context memory retrieval 94.2% Real engineering cases 30 cases, each with 20+ turns 100% Architecture Agent support Codex native hooks, MCP hidden by default <img src=

agentagent-memoryclaude-codecodexembeddingsgraph-memorylong-term-memorymemory-pluginopenclaw

Quick Facts

Stars407
Forks2
LanguageTypeScript
CategoryClaude Skill
LicenseMIT
Quality Score65.1396296722317/100
Open Issues2
Last Updated2026-05-26
Created2026-05-08
Platformsclaude-code, codex, node
Est. Tokens~228k

Compatible Skills

These tools work well together with memX for enhanced workflows:

  • Ori-Mnemos — semantic(0.35)+complementary+same_lang+similar_pop+shared_platform (62%)
  • remnic — semantic(0.46)+complementary+same_lang+similar_pop+shared_platform (61%)
  • openclaw-engram — semantic(0.41)+complementary+same_lang+similar_pop+shared_platform (59%)

memX alternative? Top 6 similar tools

Looking for a memX alternative? If you're comparing memX with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • memorix by AVIDS2 · ⭐ 791

    Open-source cross-agent memory layer for coding agents via MCP. Compatible with Claude Code, Codex, Cursor, Wi

  • remnic by joshuaswarren · ⭐ 206

    Open-source memory and context for user-aware agents: scoped memory, provenance, retrieval quality, correction

  • hipocampus by kevin-hs-sohn · ⭐ 159

    Drop-in memory harness for AI agents — 3-tier memory, compaction tree, hybrid search. One command to set up. W

  • Overture by SixHq · ⭐ 630

    Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server

  • vestige by samvallad33 · ⭐ 628

    Cognitive Deterministic Memory Security OS for Agentic AI. Deterministic root-cause retrieval that reaches bac

  • kindly-web-search-mcp-server by Shelpuk-AI-Technology-Consulting · ⭐ 388

    Kindly Web Search MCP Server: Web search + robust content retrieval for AI coding tools (Claude Code, Codex, C

More Claude Skill Tools

Explore other popular claude skill tools:

View all Claude Skill tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is memX?

memX is memX: self-learning, self-maintaining memory plugin for AI agents; native support for claude code, codex, and openclaw. It is categorized as a Claude Skill with 407 GitHub stars.

What programming language is memX written in?

memX is primarily written in TypeScript. It covers topics such as agent, agent-memory, claude-code.

How do I install or use memX?

You can find installation instructions and usage details in the memX GitHub repository at github.com/NeoLi00/memX. The project has 407 stars and 2 forks, indicating an active community.

What license does memX use?

memX is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to memX?

The top alternatives to memX on Agent Skills Hub include memorix, remnic, hipocampus. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

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:

View on GitHub → Browse Claude Skill tools