据 AlphaMoat 统计,截至 2026-10,NEXO Desktop Runtime 累计下载 7,305 次、获 3 个星标,按累计下载量在本次参与排名的 10,914 个 AI 技能中排名第 3,840 位,在「AI 智能体」分类(1,632 个)中排名第 516 位。
列表默认按累计下载量排序,也可按星标排序;详情页排名按累计下载量计算。
| 平台 | 累计下载 | 星标 | 评论 |
|---|---|---|---|
| ClawHub ↗ | 6,920 | 3 | - |
| SkillHub ↗ | 7,305 | 3 | — |
各平台的计数口径不同,统计时间不一致。
该技能说明运行时可提供本地记忆、watchdog、会话管理、后续跟进和 MCP 工具,并指导将 MCP 服务加入 OpenClaw 配置。技能卡提示安装会执行未固定版本的 npm 包并创建持久运行时,记忆会跨会话保留。启用前应审查软件包与其创建的服务文件,检查 ~/.nexo 下的数据内容和保留行为,并确认持久记忆适用于当前工作流。 文档配置面向 macOS 或 Linux,需要 Python 与 Node 包工具;审阅生成的 server,启用持久运行时前批准 MCP 配置变更及 gateway 重启。
资料发布于 2026-10-29
以下是根据技能文档生成的示例,不代表实际运行结果。
2026-09 起统计方法调整:同名技能按作者分别统计,并覆盖全部技能。图中虚线为调整前的月份,与之后的数据不直接比较,也不计算跨越调整的增长。
| 月份 | 累计下载 | 环比 | 星标 |
|---|---|---|---|
| 2026-10 | 7,305 | — | 3 |
| 2026-09 | 6,872 | — | 3 |
| 2026-08 | 6,511 | +4.0% | 3 |
| 2026-07 | 6,260 | +5.1% | 3 |
| 2026-06 | 5,954 | — | 3 |
以下是作者发布的原始文件,按纯文本显示,本站未做修改或审核;其中的链接不可点击,命令请核实后再运行。抓取于 2026-10-23。
---
name: nexo-brain
description: Runtime core for NEXO Desktop. Provides local memory, Deep Sleep, Evolution support-ticket mode, skills, watchdog, and MCP tools for the desktop product.
version: 7.38.7
metadata:
openclaw:
requires:
bins:
- python3
emoji: "N" homepage: https://nexo-desktop.com
os:
- darwin
- linux
install:
- id: npm
kind: node
package: nexo-brain
bins:
- nexo
- nexo-brain
label: Install NEXO Desktop runtime core (npm)
---
# NEXO Desktop Runtime Core
This skill installs the runtime core used by NEXO Desktop. It provides local memory, Deep Sleep, Evolution support-ticket mode, skills, watchdog, followups, and MCP tools through the existing compatibility package.
## Setup
If your OpenClaw client shows an install action for this skill, use that first. It installs the compatibility package used by the NEXO Desktop runtime via your configured Node package manager.
If you are setting it up manually, install the runtime core:
```bash
npx nexo-brain
```
After the runtime is installed, add the MCP server to your OpenClaw config (`~/.openclaw/openclaw.json`):
```json
{
"mcp": {
"servers": {
"nexo-brain": {
"command": "python3",
"args": ["~/.nexo/server.py"],
"env": {
"NEXO_HOME": "~/.nexo"
}
}
}
}
}
```
Restart the gateway: `openclaw gateway restart`
## What You Get
Key runtime capabilities include:
- **Local Memory** - semantic recall, trust scoring, sentiment detection, and continuity
- **Guard System** - checks past mistakes before code changes
- **Deep Sleep** - overnight consolidation, cleanup, and memory maintenance
- **Learnings** - error patterns and prevention rules, searchable by category
- **Session Management** - startup, heartbeat, and multi-session coordination
- **Reminders & Followups** - tracks user tasks and system verification tasks separately
- **Entities & Preferences** - remembers people, services, URLs, and observed user preferences
- **Watchdog** - local reliability checks and recovery signals
## How Memory Works
NEXO keeps local working memory and long-term memory on device:
1. **Recent context** - short-lived session and task state
2. **Working memory** - active preferences, entities, and decisions
3. **Long-term memory** - semantic search by meaning with retention controls
Deep Sleep consolidates, prunes, and merges memory so the runtime stays useful without sending private examples to public services.
## Key Tools
| Tool | When to Use |
|------|------------|
| `nexo_startup` | Once at session start — registers session, returns active sessions |
| `nexo_heartbeat` | Every interaction — updates task, checks inbox |
| `nexo_cognitive_retrieve` | Semantic search across all memories |
| `nexo_guard_check` | Before editing code — checks for past errors |
| `nexo_learning_add` | After resolving an error — prevents recurrence |
| `nexo_session_diary_write` | Before closing session — enables continuity |
| `nexo_cognitive_trust` | After user feedback — calibrates rigor level |
## Privacy
Everything stays local by default in `~/.nexo/`. Support and improvement tickets are anonymized: personal names, client data, examples, and private content are not sent.
## More Info
- [GitHub](https://github.com/wazionapps/nexo)
- [npm](https://www.npmjs.com/package/nexo-brain)
把开发过程中的经验、错误与纠正记录为 Markdown 文件,供后续复用并晋升为工作区记忆。
用自然语言描述需求,在本地与远程技能市场里找技能并给出推荐的技能。
给 AI agent 用的浏览器自动化命令行技能。
把用户纠正与自我复盘沉淀成分层记忆、并按使用情况升降级的技能。
一份为 AI 代理规划主动跟进、工作记忆与复盘流程的工作区配置指南。
指导如何创建与更新有效 Claude 技能的写作指南。
在安装第三方技能之前,按清单审查来源、权限与危险模式的技能。
把盛唐诗人李白的诗学观、意象系统与口吻,蒸馏成 AI 可调用的角色包。
数据月份:2026-10 · 下载/星标数聚合自公开技能注册库(ClawHub、SkillHub),按月更新。口径说明见数据方法。