by NeoLi00 · Codex Skill · ★ 60
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=
| Stars | 60 |
| Forks | 0 |
| Language | TypeScript |
| Category | Codex Skill |
| Quality Score | 62.9500266918046/100 |
| Open Issues | 1 |
| Last Updated | 2026-05-19 |
| Created | 2026-05-08 |
| Platforms | node |
| Est. Tokens | ~140k |
These tools work well together with openclaw-memx for enhanced workflows:
Explore other popular codex skill tools:
openclaw-memx is openclaw自学习自维护记忆插件 Long-term OpenClaw memory plugin with self-learning, self-maintenance, and relationship graph recall.. It is categorized as a Codex Skill with 60 GitHub stars.
openclaw-memx is primarily written in TypeScript. It covers topics such as agent, agent-memory, embeddings.
You can find installation instructions and usage details in the openclaw-memx GitHub repository at github.com/NeoLi00/openclaw-memx. The project has 60 stars and 0 forks, indicating an active community.