OpenManus介绍及本地部署体验

1.OpenManus介绍

OpenManus，由 MetaGPT 团队精心打造的开源项目，于2025年3月发布。它致力于模仿并改进 Manus 这一封闭式商业 AI Agent 的核心功能，为用户提供无需邀请码、可本地化部署的智能体解决方案。换句话说，OpenManus 就像一位全能的数字助手，能够在你的本地设备上运行，随时听候差遣，完成各种复杂任务。

它的出现，打破了技术领域的高墙，让每一位开发者都有机会站在同一起跑线上，快速实现诸如代码生成、数据分析、网络信息检索等复杂任务的自动化处理。无论你是独立开发者，还是大型团队的一员，OpenManus 都能为你提供强大的支持，让你专注于创造性的核心工作，而非将时间浪费在重复性任务上。

1.1 本地智能体运行

OpenManus 的一大亮点在于其本地智能体运行能力。你只需通过简单的终端指令输入任务，它便能迅速调用预先配置的语言模型（LLM），为你实现自动化的操作流程。无论是生成一段精妙的代码，还是对复杂的数据进行深度分析，亦或是执行网页交互任务，OpenManus 都能轻松应对，让你在数字化世界中游刃有余。

1.2 多工具链协同

为了更好地模拟人类的工作方式，OpenManus 搭建了一个强大的多工具链协同平台：

• Python 代码执行器：它能够实时生成并运行 Python 代码，无论是进行数学计算，还是编写自动化脚本，都能一气呵成，大大提高了工作效率。
• 浏览器自动化工具：这个工具就像你的网络向导，能够模拟人类操作，访问各种网页，提取你需要的信息，让你无需手动在海量的网络数据中大海捞针。
• 文件处理系统：文档生成、管理以及格式化输出（如生成精美的 HTML 报告）都不在话下，让信息的整理和呈现变得更加专业和便捷。
• 网络搜索工具：它能自动检索网络上的最新数据，为你的任务提供最前沿的实时支持，确保你的工作始终紧跟时代潮流。

1.3 实时反馈机制

在任务执行的过程中，OpenManus 并非一味地闷头苦干，而是通过实时反馈机制，将思考逻辑、进度更新以及中间结果以可视化日志的形式呈现给你。这样一来，你就能清晰地追踪任务的每一步进展，及时发现并解决问题，让整个工作流程更加透明和可控。

2.技术架构与实现：灵活高效的智能引擎

2.1 模块化设计

OpenManus 采用了先进的模块化设计理念，通过可插拔的工具（Tools）和系统指令（System Prompt）组合，实现了功能模块的快速扩展。就好比搭积木一样，你可以根据自己的需求，轻松地添加或调整各种功能模块，比如浏览器自动化工具、数据分析工具等，让智能体完美适配你的工作场景。

2.2 基于 LLM 的规划系统

其规划系统基于强大的语言模型（LLM），并采用了 ReAct（推理与行动）框架。这一框架能够将复杂的任务巧妙地分解为一系列可执行的子步骤，例如先收集信息，再进行分析，最后生成报告，并且能够动态地协调各个工具的调用，确保任务的高效执行。

2.3 多模型集成

OpenManus 默认支持 GPT-4o 这一主流语言模型，但它的魅力不仅于此。通过简单的配置文件修改，你可以轻松切换到其他模型，如 Claude 3.5、Qwen VL Plus 等。这种多模型集成的方式，让你能够充分利用不同模型的优势，根据具体任务选择最合适的工具，从而达到最佳的效果。

3.应用场景：无限可能的智能未来

OpenManus 的应用场景几乎涵盖了我们工作和生活的方方面面：

• 自动化办公：无论是生成周计划、整理会议纪要，还是处理 Excel 数据，OpenManus 都能为你一键搞定，让你从繁琐的日常事务中解脱出来。
• 开发者辅助：对于开发者来说，它就像一位贴心的编程伙伴，能够快速生成代码片段、协助调试程序、规划项目架构，让开发过程更加顺畅高效。
• 教育与研究：在教育领域，它能够辅助编程教学、生成教学材料；在学术研究中，又能自动整理文献资料，为科研工作提供有力支持。
• 企业级工具：企业可以利用它定制专属的数据分析工具、客户支持系统，甚至是 SEO 优化报告生成器，助力企业在激烈的市场竞争中脱颖而出。
• 创意实现：如果你是一位创意工作者，OpenManus 能够根据你的描述生成美观的 HTML 页面，或者对网站进行深度技术分析，比如 SEO 审核，让创意得以快速落地。

4.OpenManus部署

4.1 环境安装

创建新的 conda 环境：

conda create -n open_manus python=3.12
conda activate open_manus

克隆仓库：

git clone https://github.com/mannaandpoem/OpenManus.git
cd OpenManus安装依赖：

安装依赖：

pip install -r requirements.txt

4.2 配置

OpenManus 需要配置使用的 LLM API，请按以下步骤设置，我这里以本地部署的DeepSeek32B为例，如果使用官网满血版本也是差不多的，将API秘钥替换成LLM官网获取的就行。

在 config 目录创建 config.toml 文件（可从示例复制）

cp config/config.example.toml config/config.toml
vi config/config.toml

编辑 config/config.toml 添加 API 密钥和自定义设置(使用LLM官网的API方式)

# 全局 LLM 配置
[llm]
model = "gpt-4o"
base_url = "https://api.openai.com/v1"
api_key = "sk-..."  # 替换为真实 API 密钥
max_tokens = 4096
temperature = 0.0# 可选特定 LLM 模型配置
[llm.vision]
model = "gpt-4o"
base_url = "https://api.openai.com/v1"
api_key = "sk-..."  # 替换为真实 API 密钥

QWQ32B （本地）接口驱动

# 全局模型配置
[llm]
model = "qwq:latest"
base_url = "http://localhost:11434/v1"
api_key = "local123"
max_tokens = 4096
temperature = 0.0

确保ollama中的本地模型已经启动，如果是官网的不存在这个问题：

ollama run qwq:latest   # 如果是QWQ32B

快速启动

python main.py

然后通过终端输入你的创意！

我输入了写一个贪吃蛇的要求

本地部署版本的大模型，生成推理速度跟不上Agent要求，会出现报错：

如需体验开发中版本，可运行：

python run_flow.py

QWQ32B 官网驱动

使用阿里百炼的接口，百炼当前的规则是，只要首次登录就会送100万token，有效期半年。而针对QwQ模型是直接每天100万 token。

# 全局模型配置
[llm]
model = "qwen-plus" # 请换成自己的模型
base_url = "https://dashscope.aliyuncs.com/compatible-mode/v1"
api_key = "填入自己的从平台获取的Key"
max_tokens = 4096
temperature = 0.0

再次运行Python main.py

提示：Please write a Sname Game in Python for me .

这就完全没有障碍了，以下是Agent输出信息

可以看到Agent自己调用工具编写程序，自己测试和修改错，这点是与用LLM不同的，虽然生成的内容还有点问题，但整个过程自动化。

(open_manus) aic@aic-System-Product-Name:~/OpenManus$ python main.py
INFO     [browser_use] BrowserUse logging setup complete with level info
INFO     [root] Anonymized telemetry enabled. See https://docs.browser-use.com/development/telemetry for more information.
Enter your prompt (or 'exit' to quit): Please write a Sname Game in Python for me
2025-03-09 09:47:17.834 | WARNING  | __main__:main:18 - Processing your request...
2025-03-09 09:47:17.835 | INFO     | app.agent.base:run:137 - Executing step 1/30
2025-03-09 09:47:31.408 | INFO     | app.agent.toolcall:think:53 - ✨ Manus's thoughts: To create a simple name game in Python, we don't need to use all the tools you've mentioned. We can just use `python_execute` to run the Python code for the game. The game will ask the user for their name and then greet them with a personalized message.Let's write a simple Python program that asks for the player's name and then plays a guessing game with them where they have to guess a number between 1 and 20. I'll use the `python_execute` function to run this Python script.
2025-03-09 09:47:31.408 | INFO     | app.agent.toolcall:think:54 - 🛠️ Manus selected 1 tools to use
2025-03-09 09:47:31.408 | INFO     | app.agent.toolcall:think:58 - 🧰 Tools being prepared: ['python_execute']
2025-03-09 09:47:31.408 | INFO     | app.agent.toolcall:execute_tool:140 - 🔧 Activating tool: 'python_execute'...
2025-03-09 09:47:36.409 | INFO     | app.agent.toolcall:act:113 - 🎯 Tool 'python_execute' completed its mission! Result: Observed output of cmd `python_execute` executed:
{'observation': 'Execution timeout after 5 seconds', 'success': False}
2025-03-09 09:47:36.410 | INFO     | app.agent.base:run:137 - Executing step 2/30
2025-03-09 09:47:47.882 | INFO     | app.agent.toolcall:think:53 - ✨ Manus's thoughts: It seems that the execution timed out because the Python script tried to take input from stdin, which is not supported in this environment. To fix this, I will modify the game to use predefined inputs instead of waiting for user interaction. This way, I can demonstrate how the game works without requiring manual input during execution.Let's create a version of the name game that simulates user input and prints the results.
2025-03-09 09:47:47.882 | INFO     | app.agent.toolcall:think:54 - 🛠️ Manus selected 1 tools to use
2025-03-09 09:47:47.882 | INFO     | app.agent.toolcall:think:58 - 🧰 Tools being prepared: ['python_execute']
2025-03-09 09:47:47.882 | INFO     | app.agent.toolcall:execute_tool:140 - 🔧 Activating tool: 'python_execute'...
2025-03-09 09:47:47.884 | INFO     | app.agent.toolcall:act:113 - 🎯 Tool 'python_execute' completed its mission! Result: Observed output of cmd `python_execute` executed:
{'observation': "name 'random' is not defined", 'success': False}
2025-03-09 09:47:47.884 | INFO     | app.agent.base:run:137 - Executing step 3/30
2025-03-09 09:48:00.578 | INFO     | app.agent.toolcall:think:53 - ✨ Manus's thoughts: It appears there was a mistake in the code snippet I provided. The `random` module wasn't imported properly within the scope of the function. Let's correct that and also make sure to simulate the guessing process correctly, ensuring that the guess attempts are valid for demonstration purposes.I will now fix the issue and rerun the game simulation.
2025-03-09 09:48:00.579 | INFO     | app.agent.toolcall:think:54 - 🛠️ Manus selected 1 tools to use
2025-03-09 09:48:00.579 | INFO     | app.agent.toolcall:think:58 - 🧰 Tools being prepared: ['python_execute']
2025-03-09 09:48:00.579 | INFO     | app.agent.toolcall:execute_tool:140 - 🔧 Activating tool: 'python_execute'...
2025-03-09 09:48:00.581 | INFO     | app.agent.toolcall:act:113 - 🎯 Tool 'python_execute' completed its mission! Result: Observed output of cmd `python_execute` executed:
{'observation': "name 'random' is not defined", 'success': False}
2025-03-09 09:48:00.581 | INFO     | app.agent.base:run:137 - Executing step 4/30
2025-03-09 09:48:18.701 | INFO     | app.agent.toolcall:think:53 - ✨ Manus's thoughts: It seems there was a persistent issue with the execution environment recognizing the `random` module. Typically, this is a standard Python module and should be available without any issues. However, since we're encountering an unexpected problem, let's try defining the game logic again while ensuring that all used modules are properly imported.Let me correct the code once more to ensure that the random module is imported correctly and then simulate the game play. I will also limit the number of guesses to make sure the simulation does not run indefinitely. Let's try this corrected version of the name game.
2025-03-09 09:48:18.701 | INFO     | app.agent.toolcall:think:54 - 🛠️ Manus selected 1 tools to use
2025-03-09 09:48:18.701 | INFO     | app.agent.toolcall:think:58 - 🧰 Tools being prepared: ['python_execute']
2025-03-09 09:48:18.702 | INFO     | app.agent.toolcall:execute_tool:140 - 🔧 Activating tool: 'python_execute'...
2025-03-09 09:48:18.703 | INFO     | app.agent.toolcall:act:113 - 🎯 Tool 'python_execute' completed its mission! Result: Observed output of cmd `python_execute` executed:
{'observation': "name 'random' is not defined", 'success': False}
2025-03-09 09:48:18.703 | INFO     | app.agent.base:run:137 - Executing step 5/30
2025-03-09 09:48:47.581 | INFO     | app.agent.toolcall:think:53 - ✨ Manus's thoughts: It appears that there is a persistent issue with the execution environment where it does not seem to recognize the `random` module despite it being part of Python's standard library and included in the import statement. This is unusual and may be due to an environment-specific problem.Since I am unable to execute the code with `python_execute`, I will provide you with the complete Python script for the name game, which you can run on your local machine. Additionally, I will save this script as a `.py` file using the `file_saver` function so that you can download it if you wish.Here is the Python script for the name game:```python
import randomdef play_game():print('Hello! What is your name?')name = input()  # When running locally, this will wait for user input.secret_number = random.randint(1, 20)print(f'Well, {name}, I am thinking of a number between 1 and 20.')guesses_taken = 0while True:print('Take a guess.')try:guess = int(input())  # User provides a guess.guesses_taken += 1if guess < secret_number:print('Your guess is too low.')elif guess > secret_number:print('Your guess is too high.')else:break  # Correct guess; while loop ends.except ValueError:print('Please enter a valid number.')print(f'Good job, {name}! You guessed my number in {guesses_taken} guesses!')# Uncomment the following line to play the game when running the script:
# play_game()
```I will now proceed to save this script as a file.
2025-03-09 09:48:47.582 | INFO     | app.agent.toolcall:think:54 - 🛠️ Manus selected 1 tools to use
2025-03-09 09:48:47.582 | INFO     | app.agent.toolcall:think:58 - 🧰 Tools being prepared: ['file_saver']
2025-03-09 09:48:47.582 | INFO     | app.agent.toolcall:execute_tool:140 - 🔧 Activating tool: 'file_saver'...
2025-03-09 09:48:47.584 | INFO     | app.agent.toolcall:act:113 - 🎯 Tool 'file_saver' completed its mission! Result: Observed output of cmd `file_saver` executed:
Content successfully saved to number_guessing_game.py
2025-03-09 09:48:47.584 | INFO     | app.agent.base:run:137 - Executing step 6/30
2025-03-09 09:48:54.338 | INFO     | app.agent.toolcall:think:53 - ✨ Manus's thoughts: The Python script for the name game has been successfully saved to a file named `number_guessing_game.py`. You can download this file and run it on your local machine. When you execute the script, it will prompt you to enter your name and then play a guessing game where you have to guess the number between 1 and 20.If you would like to proceed with any other task or need further assistance, please let me know! Otherwise, I'll conclude this interaction now.
2025-03-09 09:48:54.339 | INFO     | app.agent.toolcall:think:54 - 🛠️ Manus selected 1 tools to use
2025-03-09 09:48:54.339 | INFO     | app.agent.toolcall:think:58 - 🧰 Tools being prepared: ['terminate']
2025-03-09 09:48:54.339 | INFO     | app.agent.toolcall:execute_tool:140 - 🔧 Activating tool: 'terminate'...
2025-03-09 09:48:54.339 | INFO     | app.agent.toolcall:_handle_special_tool:172 - 🏁 Special tool 'terminate' has completed the task!
2025-03-09 09:48:54.339 | INFO     | app.agent.toolcall:act:113 - 🎯 Tool 'terminate' completed its mission! Result: Observed output of cmd `terminate` executed:
The interaction has been completed with status: success

没有Manus邀请码，玩不了Manus，用我自己搭的openManus尝试一下Manus官网的例子

提示词如下：

Can you help me plan a two-month family trip for three people during the upcoming summer break(July to September), including one month in Australia, then New Zealand, Argentina (and other parts of South America), and Antarctica? Please include itinerary arrangements, accommodation recommendations, budget estimates, and a food guide, and then generate a detailed travel handbook. Thank you.

从openManus的输出可以看到agent主动调用Google搜索去找攻略，但是被443了，其整个处理过程从输出中可以概括如下：首先接收用户指令，然后通过浏览器自动化工具模拟人类操作访问网页、提取信息，利用网络搜索工具自动检索网络数据，为任务提供实时支持。它采用ReAct（推理与行动）框架，将复杂任务分解为可执行的子步骤，例如“收集信息→分析→生成报告”，并动态协调工具调用。在处理过程中，它遇到了网络连接问题，导致无法使用Google搜索工具获取信息，于是调整策略，基于常见知识和用户偏好，提供了旅行计划的大纲，包括行程安排、住宿建议、预算估算和美食指南。最后，它使用文件处理系统将信息整理成详细的旅行手册，保存为文本文件，并询问用户是否需要进一步的准备或等待网络恢复以获取更详细的信息。

(open_manus) aic@aic-System-Product-Name:~/OpenManus$ python main.py
INFO     [browser_use] BrowserUse logging setup complete with level info
INFO     [root] Anonymized telemetry enabled. See https://docs.browser-use.com/development/telemetry for more information.
Enter your prompt (or 'exit' to quit): Can you help me plan a two-month family trip for three people during the upcoming summer break(July to September), including one month in Australia, then New Zealand, Argentina (and other parts of South America), and Antarctica? Please include itinerary arrangements, accommodation recommendations, budget estimates, and a food guide, and then generate a detailed travel handbook. Thank you.
2025-03-09 10:07:05.843 | WARNING  | __main__:main:18 - Processing your request...
2025-03-09 10:07:05.843 | INFO     | app.agent.base:run:137 - Executing step 1/30
2025-03-09 10:07:07.781 | INFO     | app.agent.toolcall:think:53 - ✨ Manus's thoughts:
2025-03-09 10:07:07.781 | INFO     | app.agent.toolcall:think:54 - 🛠️ Manus selected 1 tools to use
2025-03-09 10:07:07.781 | INFO     | app.agent.toolcall:think:58 - 🧰 Tools being prepared: ['google_search']
2025-03-09 10:07:07.781 | INFO     | app.agent.toolcall:execute_tool:140 - 🔧 Activating tool: 'google_search'...
2025-03-09 10:07:12.849 | ERROR    | app.agent.toolcall:execute_tool:162 - ⚠️ Tool 'google_search' encountered a problem: HTTPSConnectionPool(host='www.google.com', port=443): Max retries exceeded with url: /search?q=two-month+family+trip+itinerary+Australia+New+Zealand+Argentina+South+America+Antarctica&num=12&hl=en&start=0&safe=active (Caused by NewConnectionError('<urllib3.connection.HTTPSConnection object at 0x7f70974abe00>: Failed to establish a new connection: [Errno 101] Network is unreachable'))
2025-03-09 10:07:12.850 | INFO     | app.agent.toolcall:act:113 - 🎯 Tool 'google_search' completed its mission! Result: Error: ⚠️ Tool 'google_search' encountered a problem: HTTPSConnectionPool(host='www.google.com', port=443): Max retries exceeded with url: /search?q=two-month+family+trip+itinerary+Australia+New+Zealand+Argentina+South+America+Antarctica&num=12&hl=en&start=0&safe=active (Caused by NewConnectionError('<urllib3.connection.HTTPSConnection object at 0x7f70974abe00>: Failed to establish a new connection: [Errno 101] Network is unreachable'))
2025-03-09 10:07:12.850 | INFO     | app.agent.base:run:137 - Executing step 2/30
2025-03-09 10:07:14.637 | INFO     | app.agent.toolcall:think:53 - ✨ Manus's thoughts:
2025-03-09 10:07:14.637 | INFO     | app.agent.toolcall:think:54 - 🛠️ Manus selected 1 tools to use
2025-03-09 10:07:14.637 | INFO     | app.agent.toolcall:think:58 - 🧰 Tools being prepared: ['google_search']
2025-03-09 10:07:14.637 | INFO     | app.agent.toolcall:execute_tool:140 - 🔧 Activating tool: 'google_search'...
2025-03-09 10:07:19.647 | ERROR    | app.agent.toolcall:execute_tool:162 - ⚠️ Tool 'google_search' encountered a problem: HTTPSConnectionPool(host='www.google.com', port=443): Max retries exceeded with url: /search?q=two-month+family+trip+itinerary+Australia+New+Zealand+Argentina+South+America+Antarctica&num=12&hl=en&start=0&safe=active (Caused by NewConnectionError('<urllib3.connection.HTTPSConnection object at 0x7f70974d99a0>: Failed to establish a new connection: [Errno 101] Network is unreachable'))
2025-03-09 10:07:19.647 | INFO     | app.agent.toolcall:act:113 - 🎯 Tool 'google_search' completed its mission! Result: Error: ⚠️ Tool 'google_search' encountered a problem: HTTPSConnectionPool(host='www.google.com', port=443): Max retries exceeded with url: /search?q=two-month+family+trip+itinerary+Australia+New+Zealand+Argentina+South+America+Antarctica&num=12&hl=en&start=0&safe=active (Caused by NewConnectionError('<urllib3.connection.HTTPSConnection object at 0x7f70974d99a0>: Failed to establish a new connection: [Errno 101] Network is unreachable'))
2025-03-09 10:07:19.647 | INFO     | app.agent.base:run:137 - Executing step 3/30
2025-03-09 10:07:29.691 | INFO     | app.agent.toolcall:think:53 - ✨ Manus's thoughts: It seems there is a network issue preventing us from using the Google search function to find information on the web. I will attempt to use the Google search tool again shortly, but first let's outline the general steps we'll take to plan your family trip.1. Break down the trip into segments based on location (Australia, New Zealand, Argentina and other parts of South America, Antarctica).
2. For each segment, research popular tourist destinations, activities suitable for families, and estimate travel time between locations.
3. Look up recommended accommodations that cater to families with children.
4. Create a rough budget for each country considering accommodation, food, transportation, and activities.
5. Compile a food guide that includes local cuisine recommendations and any dietary considerations for families.
6. Organize all the information into a detailed travel handbook.Since I cannot currently access online resources due to network issues, once the network is restored, I will be able to gather specific information for each part of the trip. In the meantime, if you have any preferences or specific interests for any of these locations, please let me know so I can tailor the itinerary accordingly.
2025-03-09 10:07:29.691 | INFO     | app.agent.toolcall:think:54 - 🛠️ Manus selected 1 tools to use
2025-03-09 10:07:29.691 | INFO     | app.agent.toolcall:think:58 - 🧰 Tools being prepared: ['google_search']
2025-03-09 10:07:29.692 | INFO     | app.agent.toolcall:execute_tool:140 - 🔧 Activating tool: 'google_search'...
2025-03-09 10:07:34.701 | ERROR    | app.agent.toolcall:execute_tool:162 - ⚠️ Tool 'google_search' encountered a problem: HTTPSConnectionPool(host='www.google.com', port=443): Max retries exceeded with url: /search?q=two-month+family+trip+itinerary+Australia+New+Zealand+Argentina+South+America+Antarctica&num=12&hl=en&start=0&safe=active (Caused by NewConnectionError('<urllib3.connection.HTTPSConnection object at 0x7f70974fc920>: Failed to establish a new connection: [Errno 101] Network is unreachable'))
2025-03-09 10:07:34.701 | INFO     | app.agent.toolcall:act:113 - 🎯 Tool 'google_search' completed its mission! Result: Error: ⚠️ Tool 'google_search' encountered a problem: HTTPSConnectionPool(host='www.google.com', port=443): Max retries exceeded with url: /search?q=two-month+family+trip+itinerary+Australia+New+Zealand+Argentina+South+America+Antarctica&num=12&hl=en&start=0&safe=active (Caused by NewConnectionError('<urllib3.connection.HTTPSConnection object at 0x7f70974fc920>: Failed to establish a new connection: [Errno 101] Network is unreachable'))
2025-03-09 10:07:34.701 | INFO     | app.agent.base:run:137 - Executing step 4/30
2025-03-09 10:07:37.375 | INFO     | app.agent.toolcall:think:53 - ✨ Manus's thoughts:
2025-03-09 10:07:37.375 | INFO     | app.agent.toolcall:think:54 - 🛠️ Manus selected 1 tools to use
2025-03-09 10:07:37.375 | INFO     | app.agent.toolcall:think:58 - 🧰 Tools being prepared: ['google_search']
2025-03-09 10:07:37.375 | INFO     | app.agent.toolcall:execute_tool:140 - 🔧 Activating tool: 'google_search'...
2025-03-09 10:07:42.384 | ERROR    | app.agent.toolcall:execute_tool:162 - ⚠️ Tool 'google_search' encountered a problem: HTTPSConnectionPool(host='www.google.com', port=443): Max retries exceeded with url: /search?q=two-month+family+trip+itinerary+Australia+New+Zealand+Argentina+South+America+Antarctica&num=12&hl=en&start=0&safe=active (Caused by NewConnectionError('<urllib3.connection.HTTPSConnection object at 0x7f7097511460>: Failed to establish a new connection: [Errno 101] Network is unreachable'))
2025-03-09 10:07:42.385 | INFO     | app.agent.toolcall:act:113 - 🎯 Tool 'google_search' completed its mission! Result: Error: ⚠️ Tool 'google_search' encountered a problem: HTTPSConnectionPool(host='www.google.com', port=443): Max retries exceeded with url: /search?q=two-month+family+trip+itinerary+Australia+New+Zealand+Argentina+South+America+Antarctica&num=12&hl=en&start=0&safe=active (Caused by NewConnectionError('<urllib3.connection.HTTPSConnection object at 0x7f7097511460>: Failed to establish a new connection: [Errno 101] Network is unreachable'))
2025-03-09 10:07:42.385 | INFO     | app.agent.base:run:137 - Executing step 5/30
2025-03-09 10:08:20.080 | INFO     | app.agent.toolcall:think:53 - ✨ Manus's thoughts: It appears that the network issue is persistent and preventing us from using the Google search function to gather information. In order to proceed with planning your trip, we can still make a general outline of what your two-month family trip might look like based on common itineraries for families visiting these destinations. Once the network issues are resolved, I will be able to provide more detailed and personalized information.### General Itinerary Outline#### Month 1: Australia and New Zealand
- **Australia (2 weeks)**- Sydney: Visit iconic sites such as the Opera House, Harbour Bridge, and Bondi Beach.- Great Barrier Reef: Explore one of the world's most beautiful coral reefs.- Uluru-Kata Tjuta National Park: Witness the stunning rock formations and learn about Aboriginal culture.- Melbourne: Enjoy arts, culture, and sports events.- **New Zealand (2 weeks)**- Auckland: Start in the city with museums and parks.- Rotorua: Experience geothermal wonders and Maori culture.- Queenstown: Adventure capital with activities like bungee jumping or scenic tours.- Fiordland National Park: Take a cruise through Milford Sound.#### Month 2: South America and Antarctica
- **Argentina and Other Parts of South America (3 weeks)**- Buenos Aires: Explore the vibrant city life, tango, and cuisine.- Mendoza: Wine region and Andes Mountains.- Iguazu Falls: One of the world's largest waterfall systems.- Patagonia: Glacier viewing and trekking.- Optional: Machu Picchu in Peru or the Amazon Rainforest.- **Antarctica (1 week)**- Cruise: Visit penguins, seals, and whales in their natural habitat.- Zodiac excursions: Land on the continent to explore research stations.### Accommodation Recommendations
For each destination, consider booking:
- Family-friendly hotels or resorts with amenities like pools and play areas.
- Apartments or vacation rentals for more space and home-like comfort.
- Eco-lodges in nature reserves for unique experiences.### Budget Estimates
The budget will depend on many factors including travel style, accommodation choices, and the number of activities you choose. Generally:
- Australia and New Zealand can be quite expensive due to high living costs and long distances between attractions.
- Argentina and other parts of South America tend to be more affordable except for flights.
- Antarctica cruises vary widely in price but generally start at around $5,000 per person for a week-long trip.### Food Guide
Each country has its own culinary specialties:
- Australia: Seafood, barbecue, meat pies, and multicultural dining options.
- New Zealand: Fresh seafood, lamb, and kiwi fruit.
- Argentina: Famous for its beef, empanadas, and Malbec wine.
- South America: Diverse cuisines including Peruvian ceviche and Brazilian churrasco.
- Antarctica: Meals are typically included on cruises and may feature international dishes.Once the network is operational again, I'll perform searches for more specific recommendations and current pricing. Meanwhile, if you have any preferences or specific requests for this trip, please let me know so I can incorporate them into the plan.If you would like to continue with creating a detailed travel handbook now with the available information, or wait until we can access online resources, please advise.
2025-03-09 10:08:20.080 | INFO     | app.agent.toolcall:think:54 - 🛠️ Manus selected 0 tools to use
2025-03-09 10:08:20.080 | INFO     | app.agent.base:run:137 - Executing step 6/30
2025-03-09 10:09:04.420 | INFO     | app.agent.toolcall:think:53 - ✨ Manus's thoughts: Given the ongoing network issues, I will proceed with creating a detailed travel handbook using the general outline provided. This handbook will be saved as a text file and can be expanded upon once we regain access to online resources for more specific details.I'll organize the information into sections for each part of your trip: Australia, New Zealand, Argentina and South America, and Antarctica. Each section will include a brief itinerary, accommodation recommendations, budget estimates, and a food guide based on common knowledge. Once this is done, you can review the content and let me know if any changes or additions are needed.Let's begin by drafting the text for the travel handbook.
2025-03-09 10:09:04.420 | INFO     | app.agent.toolcall:think:54 - 🛠️ Manus selected 1 tools to use
2025-03-09 10:09:04.421 | INFO     | app.agent.toolcall:think:58 - 🧰 Tools being prepared: ['file_saver']
2025-03-09 10:09:04.421 | INFO     | app.agent.toolcall:execute_tool:140 - 🔧 Activating tool: 'file_saver'...
2025-03-09 10:09:04.423 | INFO     | app.agent.toolcall:act:113 - 🎯 Tool 'file_saver' completed its mission! Result: Observed output of cmd `file_saver` executed:
Content successfully saved to travel_handbook.txt
2025-03-09 10:09:04.423 | INFO     | app.agent.base:run:137 - Executing step 7/30
2025-03-09 10:09:12.203 | INFO     | app.agent.toolcall:think:53 - ✨ Manus's thoughts: The travel handbook has been successfully created and saved as `travel_handbook.txt`. This document includes a general itinerary for each destination, accommodation recommendations, budget estimates, and a food guide based on common knowledge.Once the network issues are resolved, I will be able to provide more detailed information and tailor the plan further according to your preferences. In the meantime, you can review the current content of the travel handbook and let me know if there's anything specific you'd like to add or modify.Would you like to proceed with any other preparations for your trip, or should we wait until the network is back up to access more detailed online resources? If you have any immediate questions or need assistance with another aspect of your travel planning, please let me know.
2025-03-09 10:09:12.203 | INFO     | app.agent.toolcall:think:54 - 🛠️ Manus selected 0 tools to use
2025-03-09 10:09:12.203 | INFO     | app.agent.base:run:137 - Executing step 8/30
2025-03-09 10:09:26.233 | INFO     | app.agent.toolcall:think:53 - ✨ Manus's thoughts: Given the ongoing network issues, let's focus on what we can do offline for now. Here are a few steps we can take:1. **Review and Expand Travel Handbook**: We can review the travel handbook and expand it with more details that don't require online access, such as creating packing lists, planning activities suitable for children, or organizing entertainment for long flights.2. **Create a Budget Template**: Develop a budget template where you can input costs as you find them. This can be done in a spreadsheet format which can later be filled with actual numbers once we have internet access.3. **Prepare Travel Documents Checklist**: Make a checklist of all necessary travel documents such as passports, visas, travel insurance, and any other paperwork required for international travel.4. **Research Offline Resources**: If you have any guidebooks or travel resources available offline, we can use those to add more information to your itinerary and travel handbook.5. **Plan for Contingencies**: Think about potential challenges during the trip (e.g., lost luggage, medical emergencies) and prepare contingency plans.6. **Draft an Itinerary Schedule**: Create a draft schedule for each day or week of the trip, leaving room for flexibility and spontaneous activities.Would you like to proceed with any of these steps? Or do you have another task in mind that we could work on while we wait for the network to be restored? If you have specific preferences or requests, please let me know so I can tailor the assistance accordingly.
2025-03-09 10:09:26.233 | INFO     | app.agent.toolcall:think:54 - 🛠️ Manus selected 0 tools to use
2025-03-09 10:09:26.233 | INFO     | app.agent.base:run:137 - Executing step 9/30
2025-03-09 10:09:28.279 | INFO     | app.agent.toolcall:think:53 - ✨ Manus's thoughts:
2025-03-09 10:09:28.280 | INFO     | app.agent.toolcall:think:54 - 🛠️ Manus selected 1 tools to use
2025-03-09 10:09:28.280 | INFO     | app.agent.toolcall:think:58 - 🧰 Tools being prepared: ['terminate']
2025-03-09 10:09:28.280 | INFO     | app.agent.toolcall:execute_tool:140 - 🔧 Activating tool: 'terminate'...
2025-03-09 10:09:28.280 | INFO     | app.agent.toolcall:_handle_special_tool:172 - 🏁 Special tool 'terminate' has completed the task!
2025-03-09 10:09:28.280 | INFO     | app.agent.toolcall:act:113 - 🎯 Tool 'terminate' completed its mission! Result: Observed output of cmd `terminate` executed:
The interaction has been completed with status: success

OpenManus的输出虽然没有Manus那惊艳，但三位大神3小时的作品确实让人模版。从443错误看出，Agent中的工具库的多样性增强以及智能选择工具策略的强化才能极大提高其自动化生产能力。