# Memx

> Use when an agent needs to recall, save, inspect, or audit memX memories through the bundled MCP tools.

- Skill: `tomevault-io/memx` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add tomevault-io/memx`
- Raw SKILL.md: https://api.skillmd.com/api/skills/tomevault-io/memx/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: tomevault-io (https://skillmd.com/u/tomevault-io)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/tomevault-io/memx

---


# memX Memory

Use `memx_recall` for focused memory lookup before relying on past project details.
Use `memx_remember` only for durable, reusable facts, preferences, decisions, resources, and task state.
Use `memx_audit` or `memx_stats` when debugging whether the memory pipeline is working.

Do not write raw conversation echoes as memory. Prefer concise semantic statements that will help future turns.

---
> Source: [NeoLi00/memX](https://github.com/NeoLi00/memX) — distributed by [TomeVault](https://tomevault.io).
<!-- tomevault:4.0:skill_md:2026-06-23 -->