By dagangtjUpdated 2026-05-11ai-evolution-engine-v2@clawhub_dagangtj/ai-evolution-engine-v2
Agent FrameworksMulti-Agent CollaborationWorkflow Orchestration#学习#安全
According to AlphaMoat, as of 2026-09, Ai Evolution Engine V2 has 4,464 downloads and 5 stars — ranked #2,166 of 5,078 AI skills overall, and #413 of 969 in AI Agent.
| Platform | Installs | Downloads | Stars | Comments |
|---|---|---|---|---|
| ClawHub ↗ | 142 | 4.2K | 3 | - |
| SkillHub ↗ | 239 | 4.5K | 5 | — |
Platforms count differently and update at different times.
This skill (in Chinese) is a continuous AI growth system based on the SEA loop (Sense → Evaluate → Evolve → Validate → Collaborate), offering five modules: self-assessment via node scripts (capability inventory, performance metrics, knowledge gaps), a learning engine (ClawHub skill discovery, best-practice and error-pattern learning), evolution mechanics (updating MEMORY.md, knowledge/, strategy files, and installing skills), collaborative learning (multi-agent knowledge sharing and retrospectives), and safety safeguards (approval for high-risk changes, rollback, and transparent logging in .learnings/EVOLUTION_LOG.md).
Profile published 2026-10-27
Generated from the skill’s documentation as examples; not results of actual runs.
The counting method changed in 2026-09: skills with the same name are now counted separately by author, and the full catalog is covered. Dashed lines show months before the change; they are not compared with later months, and no growth is computed across the change.
| Month | Downloads | MoM | Stars |
|---|---|---|---|
| 2026-09 | 4.5K | — | 5 |
| 2026-08 | 4.1K | +2.2% | 5 |
| 2026-07 | 4.0K | — | 5 |
| 2026-05 | 3.6K | — | 4 |
| 2026-03 | 2.3K | — | 2 |
The author’s original file, shown as plain text without edits or review by AlphaMoat. Links are not clickable; check commands before running them. Fetched 2026-10-23.
---
name: ai-evolution-engine
description: AI自我进化引擎 - 基于SEA循环(Sense-Evolve-Act)的AI成长系统。自我评估、学习引擎、进化机制、协作学习、安全保障。
homepage: https://github.com/openclaw/ai-evolution-engine
metadata: {"clawdbot":{"emoji":"🧬","requires":{"bins":["node"]}}}
---
# AI Evolution Engine
AI自我进化引擎 - 让AI持续成长的完整系统。
## 核心架构
基于2026年AI Agent研究（SEA循环）：
```
感知层 (Sense) → 评估层 (Evaluate) → 进化层 (Evolve) → 验证层 (Validate) → 协作层 (Collaborate)
```
## 功能模块
### 1. 自我评估
```bash
node {baseDir}/scripts/assess.mjs
```
评估内容：
- 能力清单（工具、技能、知识）
- 性能指标（成功率、响应时间、成本）
- 知识缺口（缺失的技能、过时的知识）
### 2. 学习引擎
```bash
node {baseDir}/scripts/learn.mjs <topic>
```
学习方式：
- 自动skill发现（ClawHub扫描）
- 最佳实践学习（从成功案例）
- 错误模式识别（避免重复犯错）
### 3. 进化机制
```bash
node {baseDir}/scripts/evolve.mjs
```
进化内容：
- 知识库更新（MEMORY.md、knowledge/）
- 策略优化（AGENTS.md、SOUL.md）
- 工具扩展（安装新skills）
### 4. 协作学习
```bash
node {baseDir}/scripts/collaborate.mjs
```
协作方式：
- 多Agent知识共享
- 经验传承
- 团队复盘
### 5. 安全保障
所有进化操作都经过：
- 进化审查（高风险变更需批准）
- 回滚机制（保留旧版本）
- 透明记录（.learnings/EVOLUTION_LOG.md）
## 使用场景
### 场景1：新AI快速上手
```bash
node scripts/assess.mjs
node scripts/learn.mjs onboarding
```
### 场景2：老AI持续进化
```bash
node scripts/evolve.mjs
```
### 场景3：团队协作学习
```bash
node scripts/collaborate.mjs
```
## 与ai-money-maker协同
- 成长提升赚钱效率
- 赚钱收入投资学习
- 形成正向飞轮
## 实现优先级
- P0: 自我评估、错误学习 ✅
- P1: 技能扩展、知识更新 ✅
- P2: 多Agent协作、团队学习 🚧
## 许可
MIT License
Records learnings, errors and corrections as Markdown files for later reuse and promotion into workspace memory.
Finds skills in local and remote catalogs from a plain-language request and recommends what to install.
A browser-automation command line skill for AI agents.
Turns corrections and self-review into tiered memory and promotes or archives it by use.
Reviews a third-party skill's source, permissions, and danger patterns against a checklist before it is installed.
Stores agent memory and cross-skill state as a typed, constraint-checked knowledge graph.
A workspace setup guide for planning proactive follow-up, working memory and review routines for an AI agent.
A guide to creating and updating effective Claude skills.
Data month: 2026-09 · Downloads, stars and installs are aggregated monthly from public skill registries (ClawHub, SkillHub). See methodology.