Darwin-lfl · fantasy-lotus · Jun 15, 2025
diff --git a/README.md b/README.md
@@ -16,17 +16,18 @@ LangManus is a community-driven AI automation framework that builds upon the inc
 [![Demo](./assets/demo.gif)](./assets/demo.mp4)
 
 - [View on YouTube](https://youtu.be/sZCHqrQBUGk)
-- [Download Video](https://github.com/langmanus/langmanus/blob/main/assets/demo.mp4)
+- [Download Video](https://github.com/Darwin-lfl/langmanus/blob/main/assets/demo.mp4)
 
 ## Table of Contents
+
 - [Quick Start](#quick-start)
 - [Architecture](#architecture)
 - [Features](#features)
 - [Why LangManus?](#why-langmanus)
 - [Setup](#setup)
-    - [Prerequisites](#prerequisites)
-    - [Installation](#installation)
-    - [Configuration](#configuration)
+  - [Prerequisites](#prerequisites)
+  - [Installation](#installation)
+  - [Configuration](#configuration)
 - [Usage](#usage)
 - [Web UI](#web-ui)
 - [Development](#development)
@@ -38,7 +39,7 @@ LangManus is a community-driven AI automation framework that builds upon the inc
 
 ```bash
 # Clone the repository
-git clone https://github.com/langmanus/langmanus.git
+git clone https://github.com/Darwin-lfl/langmanus.git
 cd langmanus
 
 # Create and activate virtual environment through uv
@@ -77,32 +78,37 @@ The system consists of the following agents working together:
 ## Features
 
 ### Core Capabilities
+
 - 🤖 **LLM Integration**
-    - Support for open source models like Qwen
-    - OpenAI-compatible API interface
-    - Multi-tier LLM system for different task complexities
+  - Support for open source models like Qwen
+  - OpenAI-compatible API interface
+  - Multi-tier LLM system for different task complexities
 
 ### Tools and Integrations
+
 - 🔍 **Search and Retrieval**
-    - Web search via Tavily API
-    - Neural search with Jina
-    - Advanced content extraction
+  - Web search via Tavily API
+  - Neural search with Jina
+  - Advanced content extraction
 
 ### Development Features
+
 - 🐍 **Python Integration**
-    - Built-in Python REPL
-    - Code execution environment
-    - Package management with uv
+  - Built-in Python REPL
+  - Code execution environment
+  - Package management with uv
 
 ### Workflow Management
+
 - 📊 **Visualization and Control**
-    - Workflow graph visualization
-    - Multi-agent orchestration
-    - Task delegation and monitoring
+  - Workflow graph visualization
+  - Multi-agent orchestration
+  - Task delegation and monitoring
 
 ## Why LangManus?
 
 We believe in the power of open source collaboration. This project wouldn't be possible without the amazing work of projects like:
+
 - [Qwen](https://github.com/QwenLM/Qwen) for their open source LLMs
 - [Tavily](https://tavily.com/) for search capabilities
 - [Jina](https://jina.ai/) for neural search technology
@@ -165,9 +171,9 @@ CHROME_INSTANCE_PATH=/Applications/Google Chrome.app/Contents/MacOS/Google Chrom
 > **Note:**
 >
 > - The system uses different models for different types of tasks:
->     - Reasoning LLM for complex decision-making and analysis
->     - Basic LLM for simpler text-based tasks
->     - Vision-Language LLM for tasks involving image understanding
+>   - Reasoning LLM for complex decision-making and analysis
+>   - Basic LLM for simpler text-based tasks
+>   - Vision-Language LLM for tasks involving image understanding
 > - You can customize the base URLs for all LLMs independently
 > - Each LLM can use different API keys if needed
 > - Jina API key is optional. Provide your own key to access a higher rate limit (get your API key at [jina.ai](https://jina.ai/))
@@ -180,19 +186,23 @@ cp .env.example .env
 ```
 
 ### Configure Pre-commit Hook
+
 LangManus includes a pre-commit hook that runs linting and formatting checks before each commit. To set it up:
 
 1. Make the pre-commit script executable:
+
 ```bash
 chmod +x pre-commit
 ```
 
 2. Install the pre-commit hook:
+
 ```bash
 ln -s ../../pre-commit .git/hooks/pre-commit
 ```
 
 The pre-commit hook will automatically:
+
 - Run linting checks (`make lint`)
 - Run code formatting (`make format`)
 - Add any reformatted files back to staging
@@ -223,20 +233,19 @@ uv run server.py
 The API server exposes the following endpoints:
 
 - `POST /api/chat/stream`: Chat endpoint for LangGraph invoke with streaming support
-    - Request body:
-    ```json
-    {
-      "messages": [
-        {"role": "user", "content": "Your query here"}
-      ],
-      "debug": false
-    }
-    ```
-    - Returns a Server-Sent Events (SSE) stream with the agent's responses
+  - Request body:
+  ```json
+  {
+    "messages": [{ "role": "user", "content": "Your query here" }],
+    "debug": false
+  }
+  ```
+  - Returns a Server-Sent Events (SSE) stream with the agent's responses
 
 ### Advanced Configuration
 
 LangManus can be customized through various configuration files in the `src/config` directory:
+
 - `env.py`: Configure LLM models, API keys, and base URLs
 - `tools.py`: Adjust tool-specific settings (e.g., Tavily search results limit)
 - `agents.py`: Modify team composition and agent system prompts
@@ -252,20 +261,22 @@ LangManus uses a sophisticated prompting system in the `src/prompts` directory t
 - **Researcher ([`src/prompts/researcher.md`](src/prompts/researcher.md))**: Specializes in information gathering through web searches and data collection. Uses Tavily search and web crawling capabilities while avoiding mathematical computations or file operations.
 
 - **Coder ([`src/prompts/coder.md`](src/prompts/coder.md))**: Professional software engineer role focused on Python and bash scripting. Handles:
-    - Python code execution and analysis
-    - Shell command execution
-    - Technical problem-solving and implementation
+
+  - Python code execution and analysis
+  - Shell command execution
+  - Technical problem-solving and implementation
 
 - **File Manager ([`src/prompts/file_manager.md`](src/prompts/file_manager.md))**: Handles all file system operations with a focus on properly formatting and saving content in markdown format.
 
 - **Browser ([`src/prompts/browser.md`](src/prompts/browser.md))**: Web interaction specialist that handles:
-    - Website navigation
-    - Page interaction (clicking, typing, scrolling)
-    - Content extraction from web pages
+  - Website navigation
+  - Page interaction (clicking, typing, scrolling)
+  - Content extraction from web pages
 
 #### Prompt System Architecture
 
 The prompts system uses a template engine ([`src/prompts/template.py`](src/prompts/template.py)) that:
+
 - Loads role-specific markdown templates
 - Handles variable substitution (e.g., current time, team member information)
 - Formats system prompts for each agent

diff --git a/README_zh.md b/README_zh.md
@@ -18,17 +18,18 @@ LangManus 是一个社区驱动的 AI 自动化框架，它建立在开源社区
 [![Demo](./assets/demo.gif)](./assets/demo.mp4)
 
 - [在 YouTube 上观看](https://youtu.be/sZCHqrQBUGk)
-- [下载视频](https://github.com/langmanus/langmanus/blob/main/assets/demo.mp4)
+- [下载视频](https://github.com/Darwin-lfl/langmanus/blob/main/assets/demo.mp4)
 
 ## 目录
+
 - [快速开始](#快速开始)
 - [架构](#架构)
 - [功能特性](#功能特性)
 - [为什么选择 LangManus？](#为什么选择-langmanus)
 - [安装设置](#安装设置)
-    - [前置要求](#前置要求)
-    - [安装步骤](#安装步骤)
-    - [配置](#配置)
+  - [前置要求](#前置要求)
+  - [安装步骤](#安装步骤)
+  - [配置](#配置)
 - [使用方法](#使用方法)
 - [网页界面](#网页界面)
 - [开发](#开发)
@@ -41,7 +42,7 @@ LangManus 是一个社区驱动的 AI 自动化框架，它建立在开源社区
 
 ```bash
 # 克隆仓库
-git clone https://github.com/langmanus/langmanus.git
+git clone https://github.com/Darwin-lfl/langmanus.git
 cd langmanus
 
 # 用uv创建并激活虚拟环境
@@ -80,32 +81,37 @@ LangManus 实现了一个分层的多智能体系统，其中有一个主管智
 ## 功能特性
 
 ### 核心能力
+
 - 🤖 **LLM 集成**
-    - 支持通义千问等开源模型
-    - OpenAI 兼容的 API 接口
-    - 多层 LLM 系统适配不同任务复杂度
+  - 支持通义千问等开源模型
+  - OpenAI 兼容的 API 接口
+  - 多层 LLM 系统适配不同任务复杂度
 
 ### 工具和集成
+
 - 🔍 **搜索和检索**
-    - 通过 Tavily API 进行网络搜索
-    - 使用 Jina 进行神经搜索
-    - 高级内容提取
+  - 通过 Tavily API 进行网络搜索
+  - 使用 Jina 进行神经搜索
+  - 高级内容提取
 
 ### 开发特性
+
 - 🐍 **Python 集成**
-    - 内置 Python REPL
-    - 代码执行环境
-    - 使用 uv 进行包管理
+  - 内置 Python REPL
+  - 代码执行环境
+  - 使用 uv 进行包管理
 
 ### 工作流管理
+
 - 📊 **可视化和控制**
-    - 工作流程图可视化
-    - 多智能体编排
-    - 任务分配和监控
+  - 工作流程图可视化
+  - 多智能体编排
+  - 任务分配和监控
 
 ## 为什么选择 LangManus？
 
 我们信奉开源协作的力量。本项目的实现离不开以下优秀项目的支持：
+
 - [Qwen](https://github.com/QwenLM/Qwen)：提供开源语言模型
 - [Tavily](https://tavily.com/)：提供搜索能力
 - [Jina](https://jina.ai/)：提供神经搜索技术
@@ -170,9 +176,9 @@ CHROME_INSTANCE_PATH=/Applications/Google Chrome.app/Contents/MacOS/Google Chrom
 > **注意：**
 >
 > - 系统对不同类型的任务使用不同的模型：
->     - 推理 LLM 用于复杂的决策和分析
->     - 基础 LLM 用于简单的文本任务
->     - 视觉语言 LLM 用于涉及图像理解的任务
+>   - 推理 LLM 用于复杂的决策和分析
+>   - 基础 LLM 用于简单的文本任务
+>   - 视觉语言 LLM 用于涉及图像理解的任务
 > - 所有 LLM 的基础 URL 都可以独立自定义
 > - 每个 LLM 可以使用不同的 API 密钥
 > - Jina API 密钥是可选的，提供自己的密钥可以获得更高的速率限制（你可以在 [jina.ai](https://jina.ai/) 获该密钥）
@@ -185,19 +191,23 @@ cp .env.example .env
 ```
 
 ### 配置预提交钩子
+
 LangManus 包含一个预提交钩子，在每次提交前运行代码检查和格式化。设置步骤：
 
 1. 使预提交脚本可执行：
+
 ```bash
 chmod +x pre-commit
 ```
 
 2. 安装预提交钩子：
+
 ```bash
 ln -s ../../pre-commit .git/hooks/pre-commit
 ```
 
 预提交钩子将自动：
+
 - 运行代码检查（`make lint`）
 - 运行代码格式化（`make format`）
 - 将任何重新格式化的文件添加回暂存区
@@ -228,21 +238,19 @@ uv run server.py
 API 服务器提供以下端点：
 
 - `POST /api/chat/stream`：用于 LangGraph 调用的聊天端点，流式响应
-    - 请求体：
-    ```json
-    {
-      "messages": [
-        {"role": "user", "content": "在此输入您的查询"}
-      ],
-      "debug": false
-    }
-    ```
-    - 返回包含智能体响应的服务器发送事件（SSE）流
-
+  - 请求体：
+  ```json
+  {
+    "messages": [{ "role": "user", "content": "在此输入您的查询" }],
+    "debug": false
+  }
+  ```
+  - 返回包含智能体响应的服务器发送事件（SSE）流
 
 ### 高级配置
 
 LangManus 可以通过 `src/config` 目录中的各种配置文件进行自定义：
+
 - `env.py`：配置 LLM 模型、API 密钥和基础 URL
 - `tools.py`：调整工具特定设置（如 Tavily 搜索结果限制）
 - `agents.py`：修改团队组成和智能体系统提示
@@ -258,20 +266,22 @@ LangManus 在 `src/prompts` 目录中使用复杂的提示系统来定义智能
 - **研究员（[`src/prompts/researcher.md`](src/prompts/researcher.md)）**：专门通过网络搜索和数据收集来收集信息。使用 Tavily 搜索和网络爬取功能，避免数学计算或文件操作。
 
 - **程序员（[`src/prompts/coder.md`](src/prompts/coder.md)）**：专业软件工程师角色，专注于 Python 和 bash 脚本。处理：
-    - Python 代码执行和分析
-    - Shell 命令执行
-    - 技术问题解决和实现
+
+  - Python 代码执行和分析
+  - Shell 命令执行
+  - 技术问题解决和实现
 
 - **文件管理员（[`src/prompts/file_manager.md`](src/prompts/file_manager.md)）**：处理所有文件系统操作，重点是正确格式化和保存 markdown 格式的内容。
 
 - **浏览器（[`src/prompts/browser.md`](src/prompts/browser.md)）**：网络交互专家，处理：
-    - 网站导航
-    - 页面交互（点击、输入、滚动）
-    - 从网页提取内容
+  - 网站导航
+  - 页面交互（点击、输入、滚动）
+  - 从网页提取内容
 
 #### 提示系统架构
 
 提示系统使用模板引擎（[`src/prompts/template.py`](src/prompts/template.py)）来：
+
 - 加载特定角色的 markdown 模板
 - 处理变量替换（如当前时间、团队成员信息）
 - 为每个智能体格式化系统提示