​
Using the xpander CLI

1

Install the CLI

Install the xpander CLI globally:

npm install -g xpander-cli
2

Configure your credentials

Set up your API key and organization:

xpander configure

You’ll see output similar to:

You need to configure your credentials to use the Xpander CLI.
? Would you like to configure your credentials now? Yes
? Enter your Xpander API key: IhPLk2Cu5BXw5BmVBhld3p31mTpAxC892pD6O5E3
API Key: IhPL...O5E3 (first and last 4 characters shown)
✔ API key validation successful
API key saved to profile "default".
Organization ID will be auto-detected for you now...
⠏ Detecting organization ID...Organization ID detected: 8d185373-8b24-47a7-8607-3e9036b968bb
Organization ID saved to profile "default".
✔ Organization ID detected: 8d185373-8b24-47a7-8607-3e9036b968bb
Found 1 agent(s) in your organization.
Set "default" as the default profile.
Credentials stored at: /Users/david/.xpander/credentials
Profile: default

Configuration successful.
3

Create a new agent

Create your agent using the CLI:

xpander agent new

Follow the interactive prompts to define your agent’s capabilities and behavior.

4

Add tools to the AI Agent

  1. Open the AI Agent Workbench
  2. Add the HackerNews top stories operations
  3. Deploy the AI Agent.
5

Connect to your agent programmatically

The following steps show how to execute your agent created with the CLI:

from xpander import XpanderClient
from openai import OpenAI

# Initialize clients
xpander_client = XpanderClient(api_key=XPANDER_API_KEY)
openai_client = OpenAI(api_key=OPENAI_API_KEY)

# Get your agent
agent = xpander_client.agents.get(agent_id=XPANDER_AGENT_ID)
6

Execute your agent

Use the same execution pattern as shown in the Workbench approach. For more details on working with different LLM models, refer to the LLM SDKs documentation.

# Create a task for the agent
task = agent.add_task("Your task description here")

# Run the agent until completion
while not agent.is_finished():
    response = openai_client.chat.completions.create(
        model="gpt-4o",
        messages=agent.messages,
        tools=agent.get_tools(),
        tool_choice=agent.tool_choice,
        temperature=0.0
    )
            
    agent.add_messages(response.model_dump())
    
    tool_calls = XpanderClient.extract_tool_calls(llm_response=response.model_dump())
    agent.run_tools(tool_calls=tool_calls)

# Get results
execution_result = agent.retrieve_execution_result()
print("Status:", execution_result.status)
print("Result:", execution_result.result)
7

​
Example Output

# execution_result.status
Status: ExecutionStatus.COMPLETED

# execution_result.result
Result: Here are the top Hacker News stories from the last 24 hours:

1. Show HN: Nash, I made a standalone note with a single HTML file
   - Author: yevgenyhong
   - Score: 204
   - Comments: 47
   - Summary: A user has created a standalone note application using a single HTML file. This tool does not require any membership or software installation and can be used both online and offline. It is suitable for sharing content through messengers like Telegram and can also be used for hosting and blogging.
   - Link: [Read more](https://keepworking.github.io/nash/)

2. Finding Signal in the Noise: Machine Learning and the Markets (Jane Street)
   - Author: lewiscarson
   - Score: 76
   - Comments: 32
   - Summary: An article discussing the application of machine learning in financial markets, focusing on how to find meaningful signals amidst the noise.
   - Link: [Read more](https://signalsandthreads.com/finding-signal-in-the-noise/)

3. Sign in as anyone: Bypassing SAML SSO authentication with parser differentials
   - Author: campuscodi
   - Score: 200
   - Comments: 73
   - Summary: A security blog post detailing a method to bypass SAML SSO authentication using parser differentials, highlighting a significant security vulnerability.
   - Link: [Read more](https://github.blog/security/sign-in-as-anyone-bypassing-saml-sso-authentication-with-parser-differentials/)

These stories highlight a range of topics from innovative tech projects to significant security insights.

​
Troubleshooting / FAQ