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: MultiOn
description: "AgentOps and MultiOn have collaborated to simplify the monitoring of autonomous browser agents."
---
import CodeTooltip from '/snippets/add-code-tooltip.mdx'
import EnvTooltip from '/snippets/add-env-tooltip.mdx'
[MultiOn](https://www.multion.ai) is a platform for building autonomous agents.
## Adding AgentOps to MultiOn agents
<Steps>
<Step title="Install MultiOn">
<CodeGroup>
```bash pip
pip install -U multion
```
```bash poetry
poetry add multion
```
</CodeGroup>
</Step>
<Step title="Create your API keys">
* Create an [AgentOps API key](https://app.agentops.ai/settings/projects)
* Create a [MultiOn API key](https://app.multion.ai/api-keys)
</Step>
<Step title="Create a MultiOn client with an AgentOps key">
<CodeTooltip/>
<CodeGroup>
```python python
import multion
from multion.client import MultiOn
# Initialize MultiOn with both a MultiOn API key and an AgentOps API key
multion = MultiOn(
api_key=<INSERT YOUR MULTION API KEY HERE>,
agentops_api_key=<INSERT YOUR AGENTOPS API KEY HERE>
)
browse_response = multion.browse(
cmd="what three things do i get with agentops",
url="https://www.agentops.ai/",
max_steps=4,
include_screenshot=True
)
print(browse_response.message)
```
</CodeGroup>
<EnvTooltip />
</Step>
<Step title="Run your agent">
Execute your program and visit [app.agentops.ai/drilldown](https://app.agentops.ai/drilldown) to observe your MultiOn Agent! 🕵️
<Tip>
After your run, AgentOps prints a clickable url to console linking directly to your session in the Dashboard
</Tip>
<div/>{/* Intentionally blank div for newline */}
<Frame type="glass" caption="Clickable link to session">
<img height="200" src="https://github.com/AgentOps-AI/agentops/blob/main/docs/images/agentops-multion-browse.gif?raw=true" />
</Frame>
</Step>
</Steps>
## Full Examples
You can view several example notebooks [here](https://github.com/AgentOps-AI/agentops/tree/main/examples/multion):
* [Sample web browser agent using only MultiOn](https://github.com/AgentOps-AI/agentops/blob/main/examples/multion_examples/Autonomous_web_browsing.ipynb)
* [Combining a MultiOn agent with other LLMs calls](https://github.com/AgentOps-AI/agentops/blob/main/examples/multion_examples/Autonomous_web_browsing.ipynb)
* [Step-by-step tracking of browse events](https://github.com/AgentOps-AI/agentops/blob/main/examples/multion_examples/Step_by_step_web_browsing.ipynb)
* [Collecting data from a web page using the retrieve API](https://github.com/AgentOps-AI/agentops/blob/main/examples/multion_examples/Webpage_data_retrieval.ipynb)
<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="css" src="/styles/styles.css"></script>
<script type="module" src="/scripts/adjust_api_dynamically.js"></script>