daa-agent

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

DAA Agent

Create agents with Dynamic Agentic Architecture that adapt and learn over time.

创建采用Dynamic Agentic Architecture、可随时间适配与学习的智能体。

When to use

使用场景

When you need agents that go beyond static configurations — agents that adapt their behavior based on performance metrics, learn from interactions, and share knowledge with other agents.

当你需要超越静态配置的智能体时——即那些能基于性能指标调整行为、从交互中学习，并与其他智能体共享知识的智能体。

Steps

操作步骤

Create agent — call
```
mcp__claude-flow__daa_agent_create
```
with initial configuration and learning parameters
Monitor learning — call
```
mcp__claude-flow__daa_learning_status
```
to see adaptation progress
Check performance — call
```
mcp__claude-flow__daa_performance_metrics
```
for efficiency and accuracy metrics
Adapt — call
```
mcp__claude-flow__daa_agent_adapt
```
to trigger manual adaptation based on feedback
Share knowledge — call
```
mcp__claude-flow__daa_knowledge_share
```
to propagate learnings to other agents

创建智能体 — 调用
```
mcp__claude-flow__daa_agent_create
```
并传入初始配置与学习参数
监控学习进度 — 调用
```
mcp__claude-flow__daa_learning_status
```
查看适配进展
检查性能 — 调用
```
mcp__claude-flow__daa_performance_metrics
```
获取效率与准确度指标
执行适配 — 调用
```
mcp__claude-flow__daa_agent_adapt
```
，基于反馈触发手动适配
共享知识 — 调用
```
mcp__claude-flow__daa_knowledge_share
```
将学习成果传播给其他智能体

DAA vs static agents

DAA智能体与静态智能体对比

Aspect	Static Agent	DAA Agent
Behavior	Fixed configuration	Adapts over time
Learning	None	Continuous from interactions
Knowledge	Isolated	Shared across agents
Performance	Constant	Improves with use

维度	静态智能体	DAA智能体
行为	固定配置	随时间适配
学习能力	无	从交互中持续学习
知识状态	孤立存在	跨智能体共享
性能表现	保持恒定	随使用逐步提升