Manus 无邀请码，试试开源平替本地部署 OpenManus

Lcry

发布于 2025-03-16 20:20:22

34200

代码可运行

运行总次数：0

代码可运行

OpenManus 出现后，邀请码一票难求，开源项目 OpenManus 团队称仅用3 小时就实现了初步功能，网传 OpenManus 提示词以及底层使用工具被爆出，现在你不用等邀请码，本文教你本地部署开源项目 OpenManus ，可直接对接本地私有大模型。

不得不说这个开源项目短短一周多，star 截止本文发布前已经 34.1k，让子弹飞一会儿～。

本地部署教程

提前准备安装 python 3.12+ 【点击下载】和 anaconda 【点击前往】，不会的话请询问各大 ai 大模型。

创建新的 conda 环境：

conda create -n open_manus python=3.12
conda activate open_manus

克隆源码仓库

git clone https://github.com/mannaandpoem/OpenManus.git
cd OpenManus

安装必要依赖

pip install -r requirements.txt

修改默认配置文件

OpenManus 需要配置使用的 LLM API，请按以下步骤设置：

复制 config 目录下的示例配置文件：

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

编辑 config/config.toml 添加 API 密钥和自定义设置：可以替换成各大平台包括本地 ollama 的，模型必须支持必须使用支持 function calling 的模型才可以，视觉模型根据实际需要进行修改。主要修改下面的内容：

# 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

# 可选视觉模型
[llm.vision]
model = "gpt-4o"
base_url = "https://api.openai.com/v1"
api_key = "sk-..."  # 替换为真实 API 密钥
max_tokens = 8192     # Maximum number of tokens in the response
temperature = 0.0     # Controls randomness for vision model

# [llm] #AZURE OPENAI:
# api_type= 'azure'
# model = "YOUR_MODEL_NAME" #"gpt-4o-mini"
# base_url = "{YOUR_AZURE_ENDPOINT.rstrip('/')}/openai/deployments/{AZURE_DEPOLYMENT_ID}"
# api_key = "AZURE API KEY"
# max_tokens = 8096
# temperature = 0.0
# api_version="AZURE API VERSION" #"2024-08-01-preview"

# [llm] #OLLAMA:
# api_type = 'ollama'
# model = "llama3.2"
# base_url = "http://localhost:11434/v1"
# api_key = "ollama"
# max_tokens = 4096
# temperature = 0.0

# [llm.vision] #OLLAMA VISION:
# api_type = 'ollama'
# model = "llama3.2-vision"
# base_url = "http://localhost:11434/v1"
# api_key = "ollama"
# max_tokens = 4096
# temperature = 0.0

# Optional configuration for specific browser configuration
# [browser]
# Whether to run browser in headless mode (default: false)
#headless = false
# Disable browser security features (default: true)
#disable_security = true
# Extra arguments to pass to the browser
#extra_chromium_args = []
# Path to a Chrome instance to use to connect to your normal browser
# e.g. '/Applications/Google Chrome.app/Contents/MacOS/Google Chrome'
#chrome_instance_path = ""
# Connect to a browser instance via WebSocket
#wss_url = ""
# Connect to a browser instance via CDP
#cdp_url = ""

# Optional configuration, Proxy settings for the browser
# [browser.proxy]
# server = "http://proxy-server:port"
# username = "proxy-username"
# password = "proxy-password"

# Optional configuration, Search settings.
# [search]
# Search engine for agent to use. Default is "Google", can be set to "Baidu" or "DuckDuckGo".
#engine = "Google"

运行项目