diff --git a/README.md b/README.md
index fc9ce2e..143c3df 100644
--- a/README.md
+++ b/README.md
@@ -1,6 +1,6 @@
# Open Multi-Agent
-Build AI agent teams that work together. One agent plans, another implements, a third reviews — the framework handles task scheduling, dependencies, and communication automatically.
+Build AI agent teams that decompose goals into tasks automatically. Define agents with roles and tools, describe a goal — the framework plans the task graph, schedules dependencies, and runs everything in parallel.
[](https://github.com/JackChen-me/open-multi-agent/stargazers)
[](./LICENSE)
@@ -10,6 +10,7 @@ Build AI agent teams that work together. One agent plans, another implements, a
## Why Open Multi-Agent?
+- **Auto Task Decomposition** — Describe a goal in plain text. A built-in coordinator agent breaks it into a task DAG with dependencies and assignees — no manual orchestration needed.
- **Multi-Agent Teams** — Define agents with different roles, tools, and even different models. They collaborate through a message bus and shared memory.
- **Task DAG Scheduling** — Tasks have dependencies. The framework resolves them topologically — dependent tasks wait, independent tasks run in parallel.
- **Model Agnostic** — Claude, GPT, and local models (Ollama, vLLM, LM Studio) in the same team. Swap models per agent via `baseURL`.
@@ -88,6 +89,20 @@ console.log(`Success: ${result.success}`)
console.log(`Tokens: ${result.totalTokenUsage.output_tokens} output tokens`)
```
+## Three Ways to Run
+
+| Mode | Method | When to use |
+|------|--------|-------------|
+| Single agent | `runAgent()` | One agent, one prompt — simplest entry point |
+| Auto-orchestrated team | `runTeam()` | Give a goal, framework plans and executes |
+| Explicit pipeline | `runTasks()` | You define the task graph and assignments |
+
+## Contributors
+
+
+ 
+
+
## More Examples
@@ -287,13 +302,7 @@ Issues, feature requests, and PRs are welcome. Some areas where contributions wo
## Star History
-[](https://star-history.com/#JackChen-me/open-multi-agent&Date)
-
-## Contributors
-
-
-
-
+[](https://star-history.com/#JackChen-me/open-multi-agent&Date)
## License
diff --git a/README_zh.md b/README_zh.md
index 7109564..99d6352 100644
--- a/README_zh.md
+++ b/README_zh.md
@@ -1,6 +1,6 @@
# Open Multi-Agent
-构建能协同工作的 AI 智能体团队。一个智能体负责规划，一个负责实现，一个负责审查——框架自动处理任务调度、依赖关系和智能体间通信。
+构建能自动拆解目标的 AI 智能体团队。定义智能体的角色和工具，描述一个目标——框架自动规划任务图、调度依赖、并行执行。
[](https://github.com/JackChen-me/open-multi-agent/stargazers)
[](./LICENSE)
@@ -10,6 +10,7 @@
## 为什么选择 Open Multi-Agent？
+- **自动任务拆解** — 用自然语言描述目标，内置的协调者智能体自动将其拆解为带依赖关系和分配的任务图——无需手动编排。
- **多智能体团队** — 定义不同角色、工具甚至不同模型的智能体。它们通过消息总线和共享内存协作。
- **任务 DAG 调度** — 任务之间存在依赖关系。框架进行拓扑排序——有依赖的任务等待，无依赖的任务并行执行。
- **模型无关** — Claude、GPT 和本地模型（Ollama、vLLM、LM Studio）可以在同一个团队中使用。通过 `baseURL` 即可接入任何 OpenAI 兼容服务。
@@ -92,6 +93,20 @@ console.log(`成功: ${result.success}`)
console.log(`Token 用量: ${result.totalTokenUsage.output_tokens} output tokens`)
```
+## 三种运行模式
+
+| 模式 | 方法 | 适用场景 |
+|------|------|----------|
+| 单智能体 | `runAgent()` | 一个智能体，一个提示词——最简入口 |
+| 自动编排团队 | `runTeam()` | 给一个目标，框架自动规划和执行 |
+| 显式任务管线 | `runTasks()` | 你自己定义任务图和分配 |
+
+## 贡献者
+
+
+
+
+
## 更多示例
@@ -291,13 +306,7 @@ for await (const event of agent.stream('Explain monads in two sentences.')) {
## Star 趋势
-[](https://star-history.com/#JackChen-me/open-multi-agent&Date)
-
-## 贡献者
-
-
-
-
+[](https://star-history.com/#JackChen-me/open-multi-agent&Date)
## 许可证