# MEV Agent Aleph

<figure><img src="/files/ROop96fQZ2ONrgw3K1jF" alt="" width="169"><figcaption></figcaption></figure>

**Agent Aleph** is Urani's first in-house arbitrage agent, written in Python.

[**Its source code is open-sourced**](https://www.urani.trade/mev-agent-templates/aleph)**,** allowing operators to use it as a template and plug in their favorite strategies.

Agent Aleph is one of the agents running in the Protocol to help with gauging and fallback. Nevertheless, in-house agents are not intended to outperform MEV agents outsourced by operators.

***

## Current Agent Aleph's Strategies

In its first version (v1), this agent runs the following algorithm:

1️⃣ Listen for incoming batches.

2️⃣ Parse these batches to extract the order intents.

3️⃣ Check for peer-to-peer matches among the intents.

4️⃣ Spin a new thread for each intent to calculate solutions for best quotes through arbitrage in different liquidity sources.

5️⃣ Pack the solutions and send them to the protocol.

{% hint style="info" %}
More advanced strategies should be incorporated into future versions of the protocol, both in terms of arbitrage algorithms and liquidity searching.

Additionally, agents will also be responsible for the settlement, allowing the system to become fully permissionless.
{% endhint %}


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.urani.trade/mev-agents/operator-onboarding/uranis-in-house-agents/mev-agent-aleph.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.