What makes Agent Evolver notable?

1.1K downloads. Trust evidence available

How should Agent Evolver be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Agent Evolver

AI Agent self-evolution engine that enables agents to learn from experience, detect problems, extract insights, and optimize strategies autonomously. Invoke... Skill: Agent Evolver Owner: lilei0311 Summary: AI Agent self-evolution engine that enables agents to learn from experience, detect problems, extract insights, and optimize strategies autonomously. Invoke... Tags: latest:1.0.0 Version history: v1.0.0 | 2026-02-25T08:04:22.419Z | auto Initial release of agent-evolver. - Enables agents to learn from experience, detect problems, and optimize strategies autonomously. - Pr

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.1k

Updated

Oct 11, 2026

Version

1.0.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.1K downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 1.1K downloadsadoption · observed Oct 11, 2026
Latest release: 1.0.0release · observed Feb 25, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: medium.

clawhub skill install s171k5jax63a1zk2r5by9a2zes885j88:agent-evolver

Python environment detected. Create a strict virtual environment (`python -m venv .venv`) before installing dependencies to prevent system-level package conflicts.
Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-lilei0311-agent-evolver/snapshot"

Documentation

CLAWHUB

8,692 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: agent-evolver
description: AI Agent self-evolution engine that enables agents to learn from experience, detect problems, extract insights, and optimize strategies autonomously. Invoke when users need to improve agent performance, analyze execution errors, or implement continuous learning capabilities.
triggers:
  keywords:
    - "进化"
    - "优化策略"
    - "学习经验"
    - "改进"
    - "错误分析"
    - "自学习"
    - "经验"
    - "策略优化"
    - "持续学习"
    - "性能改进"
  conditions:
    - "任务执行失败超过3次"
    - "用户要求改进性能"
    - "需要分析历史错误"
    - "需要从经验中学习"
---

# Agent Evolver Skill

AI Agent 自进化引擎，让 Agent 具备自学习和持续改进能力。

## 何时使用此技能

### 自动触发条件

1. **错误分析场景**
   - 当任务执行失败时
   - 当需要分析错误原因时
   - 当需要查找相似历史错误时

2. **性能优化场景**
   - 当用户要求改进 Agent 性能时
   - 当需要优化执行策略时
   - 当需要提高成功率时

3. **学习进化场景**
   - 当需要从历史经验学习时
   - 当需要积累知识时
   - 当需要持续改进时

## 使用方法

### 1. 分析执行结果并提取经验

```bash
python3 scripts/evolution_cli.py analyze --result "<错误信息>"
python3 scripts/evolution_cli.py analyze --result-file result.json
```

### 2. 搜索相似历史经验

```bash
python3 scripts/evolution_cli.py search --query "负数平方计算错误"
python3 scripts/evolution_cli.py search --query "ValueError" --limit 10
```

### 3. 查看进化统计

```bash
python3 scripts/evolution_cli.py stats
python3 scripts/evolution_cli.py stats --agent-id my_agent --json
```

### 4. 查看进化历史

```bash
python3 scripts/evolution_cli.py history --limit 20
python3 scripts/evolution_cli.py history --task-type code_generation
```

### 5. 执行进化周期

```bash
python3 scripts/evolution_cli.py evolve "计算 -5 的平方" --task-type calculation
```

## 集成示例

### Python API

```python
from evolver_core import EvolutionManager

# 初始化进化管理器
evolver = EvolutionManager(agent_id="main_agent")

# 执行任务后自动进化
def execute_with_evolution(task):
    result = execute_task(task)
    
    # 自动分析并学习
    evolver.run_evolution(
        task_input=task,
        task_type="general"
    )
    
    return result

# 搜索历史经验
def find_similar_solutions(error_description):
    similar = evolver.search_similar(error_description)
    return similar

# 获取进化统计
def get_evolution_stats():
    return evolver.get_stats()
```

### 自动触发示例

```python
# 主 Agent 执行任务
result = execute_task("计算 -5 的平方")

# 失败后自动触发进化
if result.status == "failed":
    # 自动调用 agent-evolver 技能
    evolver = get_skill("agent-evolver")
    evolver.analyze(result.error)
    
    # 搜索相似解决方案
    similar = evolver.search_similar(result.error.message)
    
    # 应用建议的解决方案
    if similar:
        apply_solution(similar[0].solution)
```

## 功能特性

### 1. 智能经验提取
- 使用 LLM 自动分析错误原因
- 生成针对性的解决方案
- 提取关键词标签便于搜索

### 2. 经验库持久化
- SQLite 存储所有经验
- 支持按类型、错误类型查询
- 自动统计成功率、改进率

### 3. 经验向量化
- 使用 Embedding 模型向量化经验
- 支持语义搜索相似经验
- ChromaDB 向量存储

### 4. 动态策略优化
- 根据历史经验优化策略
- 支持策略版本管理
- 自动回滚机制

### 5. 多任务类型支持
- 代码生成 (code_generation)
- 数据分析 (data_analysis)
- 文档处理 (document_processing)
- 数值计算 (calculation)
- 通用任务 (general)

## 输出格式

所有命令支持 `--json` 参数输出 JSON 格式：

```bash
python3 scripts/evolution_cli.py stats --json
```

## 配置

### 环境变量

- `OPENAI_API_KEY` - OpenAI API 密钥（用于

_meta.json

{
  "ownerId": "kn79a7kh8zssw39drfxcg0ndhd80tf82",
  "slug": "agent-evolver",
  "version": "1.0.0",
  "publishedAt": 1772006662419
}

config/evolver_config.yaml

# Agent Evolver Configuration
# 智能体自进化引擎配置

# LLM 配置
llm:
  model: gpt-3.5-turbo
  temperature: 0.7
  max_tokens: 1000
  api_base: ${OPENAI_API_BASE:https://api.openai.com/v1}

# 向量化配置
vector:
  model: text-embedding-3-small
  enabled: true
  persist_directory: ~/.evolver/chroma

# 存储配置
storage:
  db_path: ~/.evolver/evolution.db
  vector_index_path: ~/.evolver/vector_index.json

# 进化配置
evolution:
  auto_optimize: true
  max_history: 1000
  similarity_threshold: 0.7
  
# 触发配置
triggers:
  auto_analyze_on_failure: true
  failure_threshold: 3
  success_sample_rate: 0.1

# 日志配置
logging:
  level: INFO
  file: ~/.evolver/evolver.log

config/skill_triggers.yaml

# Skill Triggers Configuration
# 技能触发规则配置

skills:
  agent-evolver:
    # 关键词触发
    keywords:
      - "进化"
      - "优化"
      - "学习"
      - "改进"
      - "错误分析"
      - "自学习"
      - "经验"
      - "策略优化"
      - "持续学习"
      - "性能改进"
      - "失败分析"
      - "历史经验"
    
    # 条件触发
    conditions:
      - type: "error_count"
        threshold: 3
        action: "analyze"
        description: "同一任务失败超过3次时触发分析"
      
      - type: "user_request"
        patterns:
          - "帮我改进"
          - "分析一下错误"
          - "优化一下策略"
          - "为什么失败"
          - "之前遇到过"
          - "历史经验"
        action: "evolve"
        description: "用户请求改进时触发进化"
      
      - type: "performance_drop"
        threshold: 0.1
        action: "optimize"
        description: "性能下降超过10%时触发优化"
      
      - type: "new_task_type"
        action: "learn"
        description: "遇到新任务类型时触发学习"
    
    # 自动触发
    auto_trigger:
      - event: "task_failed"
        action: "extract_experience"
        probability: 1.0
        description: "任务失败时自动提取经验"
      
      - event: "task_success"
        action: "extract_experience"
        probability: 0.1
        description: "任务成功时10%概率提取经验"
      
      - event: "periodic"
        interval: 3600
        action: "stats_report"
        description: "每小时生成统计报告"
    
    # 命令映射
    commands:
      analyze: "python3 scripts/evolution_cli.py analyze"
      search: "python3 scripts/evolution_cli.py search"
      stats: "python3 scripts/evolution_cli.py stats"
      history: "python3 scripts/evolution_cli.py history"
      evolve: "python3 scripts/evolution_cli.py evolve"

requirements.txt

# Agent Evolver Skill Dependencies
# Core
sqlite3>=3.35.0
pyyaml>=6.0

# Vector Search
chromadb>=0.4.0
openai>=1.0.0

# LLM Integration
requests>=2.28.0

# Optional: Local embedding models
# sentence-transformers>=2.2.0

Github ReposUpdated 2d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.