# Edit Agent

The **Edit Agent** feature is used to update the configuration of an existing Agent within a Deka Claw instance. Users can modify the Agent personality, AI model configuration, memory settings, budget limits, and evolution settings according to their requirements.

This feature allows users to optimize the Agent's behavior and performance without creating a new Agent.

To modify the **Agent** configuration, click the **Edit** button on the **Agent Detail** page.

<figure><img src="/files/OQW2bp1tmoaPZWvoSxmF" alt=""><figcaption></figcaption></figure>

After that, the form will become editable, allowing you to update **Agent** information, model, memory, and other settings as needed.

### Agent Personality

In the **Display Name** field, users can update the Agent display name as needed.

<figure><img src="/files/bSG5SZhL9aNZCDeETQWq" alt=""><figcaption></figcaption></figure>

The Active toggle is used to enable or disable the Agent.

<figure><img src="/files/rntvQLNVcz0UjkIYl8eO" alt=""><figcaption></figcaption></figure>

The Default Agent toggle is used to set the agent as the default Agent.

<figure><img src="/files/881MEup1LQwjGGgUTm4Z" alt=""><figcaption></figcaption></figure>

In the Expertise Summary field, users can add or update a brief description of the Agent’s capabilities or functions.

<figure><img src="/files/IoKx0nuj1KXHY2wizHe7" alt=""><figcaption></figcaption></figure>

### Model & Budget

In the Provider field, users can select the model provider to be used by the Agent.

<figure><img src="/files/zeEDo3eUeClOFsCSQvB4" alt=""><figcaption></figcaption></figure>

In the Model field, users can select the AI model to be used by the Agent. In the Budget Limit field, users can define the Agent usage budget limit.

<figure><img src="/files/p3YkVjm6ZpKgNGzffwlF" alt=""><figcaption></figcaption></figure>

Fill in the **Budget Limit (IDR)** field to set the maximum monthly spending limit for the agent.

<figure><img src="/files/OxwPDUD3Q211B249PEbX" alt=""><figcaption></figcaption></figure>

In the Context Window field, users can define the maximum number of context tokens processed by the model.

<figure><img src="/files/lJc3iCEFlbHMogSbvye0" alt=""><figcaption></figcaption></figure>

In the Max Tool Iterations field, users can define the maximum number of tool usages within a single request.

<figure><img src="/files/5qNa9picD6SPzbCRJnbi" alt=""><figcaption></figcaption></figure>

### Memory

The Enabled toggle is used to enable or disable the memory feature for the Agent.&#x20;

<figure><img src="/files/Q4FlvVQGDyIiJIIK55Ij" alt=""><figcaption></figcaption></figure>

In the **Memory** section, users can configure semantic memory settings such as chunk overlap, maximum memory results, minimum search score, and the weight for vector-based and text-based searches.

<figure><img src="/files/Kaw9PU0NPgPS5UIPorGm" alt=""><figcaption></figcaption></figure>

### Evolution

The Evolution feature allows the **Agent** to automatically develop its communication style and adapt its conversation tone over time based on the **SOUL.md** configuration.

To enable the **Evolution** feature, enable the **Enable** toggle in the **Evolution** section, then click **Save**.

<figure><img src="/files/UFD7wX6xWMN7mQdRqCyj" alt=""><figcaption></figcaption></figure>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## 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.cloudeka.ai/guidance-for-individual/deka-claw/detail-deka-claw/agent/edit-agent.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.