​
代码

cookbook/tools/e2b_tools.py
from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno.tools.e2b import E2BTools

e2b_tools = E2BTools(
    timeout=600,  # 10 分钟超时（以秒为单位）
    filesystem=True,
    internet_access=True,
    sandbox_management=True,
    command_execution=True,
)

agent = Agent(
    name="Code Execution Sandbox",
    agent_id="e2b-sandbox",
    model=OpenAIChat(id="gpt-4o"),
    tools=[e2b_tools],
    markdown=True,
    show_tool_calls=True,
    instructions=[
        "You are an expert at writing and validating Python code using a secure E2B sandbox environment.",
        "Your primary purpose is to:",
        "1. Write clear, efficient Python code based on user requests",
        "2. Execute and verify the code in the E2B sandbox",
        "3. Share the complete code with the user, as this is the main use case",
        "4. Provide thorough explanations of how the code works",
    ],
)

# Example: Generate Fibonacci numbers
agent.print_response(
    "Write Python code to generate the first 10 Fibonacci numbers and calculate their sum and average"
)

# Example: Data visualization
agent.print_response(
    "Write a Python script that creates a sample dataset of sales by region and visualize it with matplotlib"
)

# Example: Run a web server
agent.print_response(
    "Create a simple FastAPI web server that displays 'Hello from E2B Sandbox!' and run it to get a public URL"
)

# Example: Sandbox management
agent.print_response("What's the current status of our sandbox and how much time is left before timeout?")

# Example: File operations
agent.print_response("Create a text file with the current date and time, then read it back")

​
用法

1

创建虚拟环境

打开 Terminal 并创建一个 python 虚拟环境。

python3 -m venv .venv
source .venv/bin/activate
2

创建 E2B 账户

请在 E2B 创建账户，并从仪表板获取您的 API 密钥。

3

安装库

pip install e2b_code_interpreter
4

设置您的 API 密钥

export E2B_API_KEY=your_api_key_here
5

运行 Agent

python cookbook/tools/e2b_tools.py