Python SDK for AI agent monitoring, LLM cost tracking, benchmarking, and more. Integrates with most LLMs and agent frameworks including CrewAI, Agno, OpenAI Agents SDK, Langchain, Autogen, AG2, and CamelAI
Python agentagentopsagents-sdkaianthropicautogencost-estimationcrewaievalsevaluation-metricsgroqlangchainllmmistralollamaopenaiopenai-agents
---
title: 'Xpander'
description: 'Xpander coding agent example with AgentOps'
---
{/* SOURCE_FILE: examples/xpander/coding_agent.py */}
_View Python Example on <a href={'https://github.com/AgentOps-AI/agentops/blob/main/examples/xpander/coding_agent.py'} target={'_blank'}>Github</a>_
This example demonstrates a complete Xpander coding agent implementation with AgentOps instrumentation using callback handlers. The example shows how to build a single-file agent that combines the MyAgent class and XpanderEventListener for comprehensive monitoring.
## Key Features
- **Single-file implementation** combining agent logic and event handling
- **Callback-based instrumentation** using XpanderEventListener
- **Async tool execution** with proper error handling and logging
- **AgentOps integration** with custom trace names and tags
## Running the Example
1. Set up your environment variables in a `.env` file or export them:
```bash
AGENTOPS_API_KEY=your_agentops_api_key
XPANDER_API_KEY=your_xpander_api_key
XPANDER_AGENT_ID=your_agent_id
OPENAI_API_KEY=your_openai_api_key
```
2. Run the agent:
```bash
python examples/xpander/coding_agent.py
```
The agent will start an interactive session where you can ask coding questions and see the results tracked in your AgentOps dashboard.
<script type="module" src="/scripts/github_stars.js"></script>
<script type="module" src="/scripts/scroll-img-fadein-animation.js"></script>
<script type="module" src="/scripts/button_heartbeat_animation.js"></script>
<script type="module" src="/scripts/adjust_api_dynamically.js"></script>