@@ -27,115 +33,115 @@
-Welcome to AutoAgent! AutoAgent is a **Fully-Automated** and highly **Self-Developing** framework that enables users to create and deploy LLM agents through **Natural Language Alone**.
+欢迎使用 AutoAgent！AutoAgent 是一个**全自动化（Fully-Automated）**且高度**自演进（Self-Developing）**的框架，让用户仅凭**自然语言**即可创建并部署 LLM Agent。
-## ✨Key Features of AutoAgent
+## ✨ AutoAgent 核心特性
-* 💬 **Natural Language-Driven Agent Building**
-Automatically constructs and orchestrates collaborative agent systems purely through natural dialogue, eliminating the need for manual coding or technical configuration.
+* 💬 **自然语言驱动的 Agent 构建**
+纯粹通过自然对话即可自动构建并编排协作式 Agent 系统，无需手动编码或技术配置。
-* 🚀 **Zero-Code Framework**
-Democratizes AI development by allowing anyone, regardless of coding experience, to create and customize their own agents, tools, and workflows using natural language alone.
+* 🚀 **零代码框架（Zero-Code Framework）**
+让任何人——无论是否具备编程经验——都能仅凭自然语言创建并定制自己的 Agent、工具与工作流，从而普及 AI 开发。
-* ⚡ **Self-Managing Workflow Generation**
-Dynamically creates, optimizes and adapts agent workflows based on high-level task descriptions, even when users cannot fully specify implementation details.
+* ⚡ **自管理工作流生成**
+根据高层任务描述动态创建、优化并适配 Agent 工作流，即使用户无法完整说明实现细节也能胜任。
-* 🔧 **Intelligent Resource Orchestration**
-Enables controlled code generation for creating tools, agents, and workflows through iterative self-improvement, supporting both single agent creation and multi-agent workflow generation.
+* 🔧 **智能资源编排**
+通过迭代式自我改进实现可控的代码生成，用于创建工具、Agent 与工作流，同时支持单 Agent 创建与多 Agent 工作流生成。
-* 🎯 **Self-Play Agent Customization**
-Enables controlled code generation for creating tools, agents, and workflows through iterative self-improvement, supporting both single agent creation and multi-agent workflow generation.
+* 🎯 **自对弈 Agent 定制（Self-Play Agent Customization）**
+通过迭代式自我改进实现可控的代码生成，用于创建工具、Agent 与工作流，同时支持单 Agent 创建与多 Agent 工作流生成。
-🚀 Unlock the Future of LLM Agents. Try 🔥AutoAgent🔥 Now!
+🚀 解锁 LLM Agent 的未来。立即体验 🔥AutoAgent🔥！
- Quick Overview of AutoAgent.
+ AutoAgent 快速概览。
-## 🔥 News
+## 🔥 动态
-
[2025, Feb 17]: 🎉🎉We've updated and released AutoAgent v0.2.0 (formerly known as MetaChain). Detailed changes include: 1) fix the bug of different LLM providers from issues; 2) add automatic installation of AutoAgent in the container environment according to issues; 3) add more easy-to-use commands for the CLI mode. 4) Rename the project to AutoAgent for better understanding.
-
[2025, Feb 10]: 🎉🎉We've released MetaChain!, including framework, evaluation codes and CLI mode! Check our paper for more details.
-### 2. `agent editor` (Agent Creation without Workflow)
+### 2. `agent editor`（无工作流的 Agent 创建）
-The most distinctive feature of AutoAgent is its natural language customization capability. Unlike other agent frameworks, AutoAgent allows you to create tools, agents, and workflows using natural language alone. Simply choose `agent editor` or `workflow editor` mode to start your journey of building agents through conversations.
+AutoAgent 最鲜明的特性是其自然语言定制能力。与其他 Agent 框架不同，AutoAgent 让你仅凭自然语言即可创建工具、Agent 与工作流。只需选择 `agent editor` 或 `workflow editor` 模式，即可通过对话开启 Agent 构建之旅。
-You can use `agent editor` as shown in the following figure.
+你可以如下方图示使用 `agent editor`。
- Input what kind of agent you want to create.
+ 输入你想创建的 Agent 类型。
- Automated agent profiling.
+ 自动化 Agent 画像分析。
- Output the agent profiles.
+ 输出 Agent 画像。
@@ -144,43 +150,43 @@ You can use `agent editor` as shown in the following figure.
- Create the desired tools.
+ 创建所需工具。
- Input what do you want to complete with the agent. (Optional)
+ 输入你希望用 Agent 完成的任务。（可选）
- Create the desired agent(s) and go to the next step.
+ 创建所需 Agent 并进入下一步。
-### 3. `workflow editor` (Agent Creation with Workflow)
+### 3. `workflow editor`（通过工作流创建 Agent）
-You can also create the agent workflows using natural language description with the `workflow editor` mode, as shown in the following figure. (Tips: this mode does not support tool creation temporarily.)
+你也可以使用 `workflow editor` 模式，通过自然语言描述来创建 Agent 工作流，如下图所示。（提示：该模式暂不支持工具创建。）
- Input what kind of workflow you want to create.
+ 输入你想要创建的工作流类型。
- Automated workflow profiling.
+ 自动化工作流画像分析。
- Output the workflow profiles.
+ 输出工作流画像。
@@ -189,25 +195,25 @@ You can also create the agent workflows using natural language description with
- Input what do you want to complete with the workflow. (Optional)
+ 输入你想通过该工作流完成的任务。（可选）
- Create the desired workflow(s) and go to the next step.
+ 创建所需的工作流并进入下一步。
-## ⚡ Quick Start
+## ⚡ 快速开始
-### Installation
+### 安装
-#### AutoAgent Installation
+#### AutoAgent 安装
```bash
git clone https://github.com/HKUDS/AutoAgent.git
@@ -215,15 +221,15 @@ cd AutoAgent
pip install -e .
```
-#### Docker Installation
+#### Docker 安装
-We use Docker to containerize the agent-interactive environment. So please install [Docker](https://www.docker.com/) first. You don't need to manually pull the pre-built image, because we have let Auto-Deep-Research **automatically pull the pre-built image based on your architecture of your machine**.
+我们使用 Docker 将 Agent 交互环境容器化。因此请先安装 [Docker](https://www.docker.com/)。你无需手动拉取预构建镜像，因为我们已让 Auto-Deep-Research **根据你的机器架构自动拉取对应的预构建镜像**。
-### API Keys Setup
+### API 密钥配置
-Create an environment variable file, just like `.env.template`, and set the API keys for the LLMs you want to use. Not every LLM API Key is required, use what you need.
+创建环境变量文件，就像 `.env.template` 一样，并为你想要使用的 LLM 设置 API 密钥。并非每个 LLM API 密钥都必须填写，按需使用即可。
```bash
# Required Github Tokens of your own
@@ -241,40 +247,40 @@ XAI_API_KEY=
-### Start with CLI Mode
+### 以 CLI 模式启动
-> [🚨 **News**: ] We have updated a more easy-to-use command to start the CLI mode and fix the bug of different LLM providers from issues. You can follow the following steps to start the CLI mode with different LLM providers with much less configuration.
+> [🚨 **最新消息**：] 我们已更新更易用的命令来启动 CLI 模式，并修复了 issues 中不同 LLM 提供商的相关 bug。你可以按照以下步骤，用更少的配置在不同 LLM 提供商下启动 CLI 模式。
-#### Command Options:
+#### 命令选项：
-You can run `auto main` to start full part of AutoAgent, including `user mode`, `agent editor` and `workflow editor`. Btw, you can also run `auto deep-research` to start more lightweight `user mode`, just like the [Auto-Deep-Research](https://github.com/HKUDS/Auto-Deep-Research) project. Some configuration of this command is shown below.
+你可以运行 `auto main` 来启动 AutoAgent 的完整功能，包括 `user mode`、`agent editor` 和 `workflow editor`。顺便一提，你也可以运行 `auto deep-research` 来启动更轻量的 `user mode`，类似于 [Auto-Deep-Research](https://github.com/HKUDS/Auto-Deep-Research) 项目。该命令的部分配置如下所示。
-- `--container_name`: Name of the Docker container (default: 'deepresearch')
-- `--port`: Port for the container (default: 12346)
-- `COMPLETION_MODEL`: Specify the LLM model to use, you should follow the name of [Litellm](https://github.com/BerriAI/litellm) to set the model name. (Default: `claude-3-5-sonnet-20241022`)
-- `DEBUG`: Enable debug mode for detailed logs (default: False)
-- `API_BASE_URL`: The base URL for the LLM provider (default: None)
-- `FN_CALL`: Enable function calling (default: None). Most of time, you could ignore this option because we have already set the default value based on the model name.
-- `git_clone`: Clone the AutoAgent repository to the local environment (only support with the `auto main` command, default: True)
-- `test_pull_name`: The name of the test pull. (only support with the `auto main` command, default: 'autoagent_mirror')
+- `--container_name`：Docker 容器名称（默认：'deepresearch'）
+- `--port`：容器端口（默认：12346）
+- `COMPLETION_MODEL`：指定要使用的 LLM 模型，模型名称应遵循 [Litellm](https://github.com/BerriAI/litellm) 的命名规范。（默认：`claude-3-5-sonnet-20241022`）
+- `DEBUG`：启用调试模式以输出详细日志（默认：False）
+- `API_BASE_URL`：LLM 提供商的基础 URL（默认：None）
+- `FN_CALL`：启用 function calling（默认：None）。大多数情况下你可以忽略此选项，因为我们已根据模型名称设置了默认值。
+- `git_clone`：将 AutoAgent 仓库克隆到本地环境（仅支持 `auto main` 命令，默认：True）
+- `test_pull_name`：测试拉取的分支名称。（仅支持 `auto main` 命令，默认：'autoagent_mirror'）
-#### More details about `git_clone` and `test_pull_name`]
+#### 关于 `git_clone` 和 `test_pull_name` 的更多说明]
-In the `agent editor` and `workflow editor` mode, we should clone a mirror of the AutoAgent repository to the local agent-interactive environment and let our **AutoAgent** automatically update the AutoAgent itself, such as creating new tools, agents and workflows. So if you want to use the `agent editor` and `workflow editor` mode, you should set the `git_clone` to True and set the `test_pull_name` to 'autoagent_mirror' or other branches.
+在 `agent editor` 和 `workflow editor` 模式下，我们需要将 AutoAgent 仓库的镜像克隆到本地 Agent 交互环境，并让 **AutoAgent** 自动更新 AutoAgent 自身，例如创建新工具、Agent 和工作流。因此，如果你想使用 `agent editor` 和 `workflow editor` 模式，应将 `git_clone` 设为 True，并将 `test_pull_name` 设为 'autoagent_mirror' 或其他分支。
-#### `auto main` with different LLM Providers
+#### 搭配不同 LLM 提供商使用 `auto main`
-Then I will show you how to use the full part of AutoAgent with the `auto main` command and different LLM providers. If you want to use the `auto deep-research` command, you can refer to the [Auto-Deep-Research](https://github.com/HKUDS/Auto-Deep-Research) project for more details.
+接下来我将演示如何通过 `auto main` 命令搭配不同 LLM 提供商使用 AutoAgent 的完整功能。如果你想使用 `auto deep-research` 命令，可参考 [Auto-Deep-Research](https://github.com/HKUDS/Auto-Deep-Research) 项目了解更多详情。
##### Anthropic
-* set the `ANTHROPIC_API_KEY` in the `.env` file.
+* 在 `.env` 文件中设置 `ANTHROPIC_API_KEY`。
```bash
ANTHROPIC_API_KEY=your_anthropic_api_key
```
-* run the following command to start Auto-Deep-Research.
+* 运行以下命令启动 Auto-Deep-Research。
```bash
auto main # default model is claude-3-5-sonnet-20241022
@@ -282,13 +288,13 @@ auto main # default model is claude-3-5-sonnet-20241022
##### OpenAI
-* set the `OPENAI_API_KEY` in the `.env` file.
+* 在 `.env` 文件中设置 `OPENAI_API_KEY`。
```bash
OPENAI_API_KEY=your_openai_api_key
```
-* run the following command to start Auto-Deep-Research.
+* 运行以下命令启动 Auto-Deep-Research。
```bash
COMPLETION_MODEL=gpt-4o auto main
@@ -296,13 +302,13 @@ COMPLETION_MODEL=gpt-4o auto main
##### Mistral
-* set the `MISTRAL_API_KEY` in the `.env` file.
+* 在 `.env` 文件中设置 `MISTRAL_API_KEY`。
```bash
MISTRAL_API_KEY=your_mistral_api_key
```
-* run the following command to start Auto-Deep-Research.
+* 运行以下命令启动 Auto-Deep-Research。
```bash
COMPLETION_MODEL=mistral/mistral-large-2407 auto main
@@ -310,13 +316,13 @@ COMPLETION_MODEL=mistral/mistral-large-2407 auto main
##### Gemini - Google AI Studio
-* set the `GEMINI_API_KEY` in the `.env` file.
+* 在 `.env` 文件中设置 `GEMINI_API_KEY`。
```bash
GEMINI_API_KEY=your_gemini_api_key
```
-* run the following command to start Auto-Deep-Research.
+* 运行以下命令启动 Auto-Deep-Research。
```bash
COMPLETION_MODEL=gemini/gemini-2.0-flash auto main
@@ -324,13 +330,13 @@ COMPLETION_MODEL=gemini/gemini-2.0-flash auto main
##### Huggingface
-* set the `HUGGINGFACE_API_KEY` in the `.env` file.
+* 在 `.env` 文件中设置 `HUGGINGFACE_API_KEY`。
```bash
HUGGINGFACE_API_KEY=your_huggingface_api_key
```
-* run the following command to start Auto-Deep-Research.
+* 运行以下命令启动 Auto-Deep-Research。
```bash
COMPLETION_MODEL=huggingface/meta-llama/Llama-3.3-70B-Instruct auto main
@@ -338,43 +344,43 @@ COMPLETION_MODEL=huggingface/meta-llama/Llama-3.3-70B-Instruct auto main
##### Groq
-* set the `GROQ_API_KEY` in the `.env` file.
+* 在 `.env` 文件中设置 `GROQ_API_KEY`。
```bash
GROQ_API_KEY=your_groq_api_key
```
-* run the following command to start Auto-Deep-Research.
+* 运行以下命令启动 Auto-Deep-Research。
```bash
COMPLETION_MODEL=groq/deepseek-r1-distill-llama-70b auto main
```
-##### OpenAI-Compatible Endpoints (e.g., Grok)
+##### OpenAI 兼容端点（例如 Grok）
-* set the `OPENAI_API_KEY` in the `.env` file.
+* 在 `.env` 文件中设置 `OPENAI_API_KEY`。
```bash
OPENAI_API_KEY=your_api_key_for_openai_compatible_endpoints
```
-* run the following command to start Auto-Deep-Research.
+* 运行以下命令启动 Auto-Deep-Research。
```bash
COMPLETION_MODEL=openai/grok-2-latest API_BASE_URL=https://api.x.ai/v1 auto main
```
-##### OpenRouter (e.g., DeepSeek-R1)
+##### OpenRouter（例如 DeepSeek-R1）
-We recommend using OpenRouter as LLM provider of DeepSeek-R1 temporarily. Because official API of DeepSeek-R1 can not be used efficiently.
+我们暂时建议使用 OpenRouter 作为 DeepSeek-R1 的 LLM 提供商，因为 DeepSeek-R1 的官方 API 目前无法高效使用。
-* set the `OPENROUTER_API_KEY` in the `.env` file.
+* 在 `.env` 文件中设置 `OPENROUTER_API_KEY`。
```bash
OPENROUTER_API_KEY=your_openrouter_api_key
```
-* run the following command to start Auto-Deep-Research.
+* 运行以下命令启动 Auto-Deep-Research。
```bash
COMPLETION_MODEL=openrouter/deepseek/deepseek-r1 auto main
@@ -382,73 +388,73 @@ COMPLETION_MODEL=openrouter/deepseek/deepseek-r1 auto main
##### DeepSeek
-* set the `DEEPSEEK_API_KEY` in the `.env` file.
+* 在 `.env` 文件中设置 `DEEPSEEK_API_KEY`。
```bash
DEEPSEEK_API_KEY=your_deepseek_api_key
```
-* run the following command to start Auto-Deep-Research.
+* 运行以下命令启动 Auto-Deep-Research。
```bash
COMPLETION_MODEL=deepseek/deepseek-chat auto main
```
-After the CLI mode is started, you can see the start page of AutoAgent:
+CLI 模式启动后，你将看到 AutoAgent 的启动页面：
- Start Page of AutoAgent.
+ AutoAgent 启动页面。
-### Tips
+### 提示
-#### Import browser cookies to browser environment
+#### 将浏览器 Cookie 导入浏览器环境
-You can import the browser cookies to the browser environment to let the agent better access some specific websites. For more details, please refer to the [cookies](./AutoAgent/environment/cookie_json/README.md) folder.
+你可以将浏览器 Cookie 导入浏览器环境，以便 Agent 更好地访问某些特定网站。更多详情，请参阅 [cookies](./AutoAgent/environment/cookie_json/README.md) 文件夹。
-#### Add your own API keys for third-party Tool Platforms
+#### 为第三方工具平台添加你自己的 API 密钥
-If you want to create tools from the third-party tool platforms, such as RapidAPI, you should subscribe tools from the platform and add your own API keys by running [process_tool_docs.py](./process_tool_docs.py).
+如果你想从第三方工具平台（例如 RapidAPI）创建工具，需要先在平台上订阅相关工具，然后通过运行 [process_tool_docs.py](./process_tool_docs.py) 添加你自己的 API 密钥。
```bash
python process_tool_docs.py
```
-More features coming soon! 🚀 **Web GUI interface** under development.
+更多功能即将推出！🚀 **Web GUI 界面**正在开发中。
-## ☑️ Todo List
+## ☑️ 待办清单
-AutoAgent is continuously evolving! Here's what's coming:
+AutoAgent 正在持续演进！以下是即将推出的内容：
-- 📊 **More Benchmarks**: Expanding evaluations to **SWE-bench**, **WebArena**, and more
-- 🖥️ **GUI Agent**: Supporting *Computer-Use* agents with GUI interaction
-- 🔧 **Tool Platforms**: Integration with more platforms like **Composio**
-- 🏗️ **Code Sandboxes**: Supporting additional environments like **E2B**
-- 🎨 **Web Interface**: Developing comprehensive GUI for better user experience
+- 📊 **更多基准测试**：将评估范围扩展到 **SWE-bench**、**WebArena** 等
+- 🖥️ **GUI Agent**：支持具备 GUI 交互的 *Computer-Use* 智能体
+- 🔧 **工具平台**：与 **Composio** 等更多平台集成
+- 🏗️ **代码沙箱**：支持 **E2B** 等更多环境
+- 🎨 **Web 界面**：开发完善的 GUI，以提升用户体验
-Have ideas or suggestions? Feel free to open an issue! Stay tuned for more exciting updates! 🚀
+有想法或建议？欢迎提交 issue！敬请期待更多精彩更新！🚀
-## 🔬 How To Reproduce the Results in the Paper
+## 🔬 如何复现论文中的结果
### GAIA Benchmark
-For the GAIA benchmark, you can run the following command to run the inference.
+对于 GAIA 基准测试，你可以运行以下命令进行推理。
```bash
cd path/to/AutoAgent && sh evaluation/gaia/scripts/run_infer.sh
```
-For the evaluation, you can run the following command.
+进行评估时，你可以运行以下命令。
```bash
cd path/to/AutoAgent && python evaluation/gaia/get_score.py
@@ -456,39 +462,39 @@ cd path/to/AutoAgent && python evaluation/gaia/get_score.py
### Agentic-RAG
-For the Agentic-RAG task, you can run the following command to run the inference.
+对于 Agentic-RAG 任务，你可以运行以下命令进行推理。
-Step1. Turn to [this page](https://huggingface.co/datasets/yixuantt/MultiHopRAG) and download it. Save them to your datapath.
+Step1. 前往[此页面](https://huggingface.co/datasets/yixuantt/MultiHopRAG) 并下载。将其保存到你的数据路径。
-Step2. Run the following command to run the inference.
+Step2. 运行以下命令进行推理。
```bash
cd path/to/AutoAgent && sh evaluation/multihoprag/scripts/run_rag.sh
```
-Step3. The result will be saved in the `evaluation/multihoprag/result.json`.
+Step3. 结果将保存在 `evaluation/multihoprag/result.json` 中。
-## 📖 Documentation
+## 📖 文档
-A more detailed documentation is coming soon 🚀, and we will update in the [Documentation](https://AutoAgent-ai.github.io/docs) page.
+更详细的文档即将推出 🚀，我们将在 [Documentation](https://AutoAgent-ai.github.io/docs) 页面持续更新。
-## 🤝 Join the Community
+## 🤝 加入社区
-We want to build a community for AutoAgent, and we welcome everyone to join us. You can join our community by:
+我们希望为 AutoAgent 建立一个社区，欢迎所有人加入我们。你可以通过以下方式加入我们的社区：
-- [Join our Slack workspace](https://join.slack.com/t/AutoAgent-workspace/shared_invite/zt-2zibtmutw-v7xOJObBf9jE2w3x7nctFQ) - Here we talk about research, architecture, and future development.
-- [Join our Discord server](https://discord.gg/z68KRvwB) - This is a community-run server for general discussion, questions, and feedback.
-- [Read or post Github Issues](https://github.com/HKUDS/AutoAgent/issues) - Check out the issues we're working on, or add your own ideas.
+- [加入我们的 Slack 工作区](https://join.slack.com/t/AutoAgent-workspace/shared_invite/zt-2zibtmutw-v7xOJObBf9jE2w3x7nctFQ) - 在这里我们讨论研究、架构和未来开发。
+- [加入我们的 Discord 服务器](https://discord.gg/z68KRvwB) - 这是一个由社区运营的服务器，用于一般讨论、提问和反馈。
+- [阅读或提交 Github Issues](https://github.com/HKUDS/AutoAgent/issues) - 查看我们正在处理的 issue，或提出你自己的想法。
-## Misc
+## 其他
@@ -500,14 +506,14 @@ We want to build a community for AutoAgent, and we welcome everyone to join us.
-## 🙏 Acknowledgements
+## 🙏 致谢
-Rome wasn't built in a day. AutoAgent stands on the shoulders of giants, and we are deeply grateful for the outstanding work that came before us. Our framework architecture draws inspiration from [OpenAI Swarm](https://github.com/openai/swarm), while our user mode's three-agent design benefits from [Magentic-one](https://github.com/microsoft/autogen/tree/main/python/packages/autogen-magentic-one)'s insights. We've also learned from [OpenHands](https://github.com/All-Hands-AI/OpenHands) for documentation structure and many other excellent projects for agent-environment interaction design, among others. We express our sincere gratitude and respect to all these pioneering works that have been instrumental in shaping AutoAgent.
+罗马非一日建成。AutoAgent 站在巨人的肩膀上，我们对前人的杰出工作深表感激。我们的框架架构借鉴了 [OpenAI Swarm](https://github.com/openai/swarm),，而用户模式下的三智能体设计则受益于 [Magentic-one](https://github.com/microsoft/autogen/tree/main/python/packages/autogen-magentic-one)'s 的见解。我们还从 [OpenHands](https://github.com/All-Hands-AI/OpenHands) 学习了文档结构，并从许多其他优秀项目中学习了智能体-环境交互设计等。我们对所有这些在塑造 AutoAgent 过程中发挥重要作用的开拓性工作致以诚挚的感谢与敬意。
-## 🌟 Cite
+## 🌟 引用
```tex
@misc{AutoAgent,
@@ -520,8 +526,3 @@ Rome wasn't built in a day. AutoAgent stands on the shoulders of giants, and we
url={https://arxiv.org/abs/2502.05957},
}
```
-
-
-
-
-
- 
- 
- 
-
+ 
- 
- 
+ 
- 
-