Code Tools Usage Guide

Tools

Cherry Studio v1.5.7 introduces an easy-to-use, powerful Code Agent feature that allows you to directly launch and manage various AI programming agents. This tutorial will guide you through the complete setup and launch process.


Steps

1. Upgrade Cherry Studio

First, please make sure your Cherry Studio is upgraded to v1.5.7 or a newer version. You can go to GitHub Releases or the official website to download the latest version.

2. Adjust the navigation bar position

To facilitate using the top tab feature, we recommend moving the navigation bar to the top.

  • Path:Settings -> Display Settings -> Navigation Bar Settings

  • Set the “Navigation Bar Position” option to Top.

3. Create a new tab

Click the “+” icon at the top of the interface to create a new blank tab.

4. Open the Code Agent feature

In the new tab, click Code(or </>) icon to enter the Code Agent configuration interface.

5. Choose a CLI tool

Choose a Code Agent tool to use based on your needs and the API Key you have. The following are currently supported:

  • Claude Code

  • Gemini CLI

  • Qwen Code

  • OpenAI Codex

6. Choose the model the Agent will call

In the model dropdown list, select a model compatible with the CLI tool you chose. (For detailed model compatibility information, please refer to the “Important Notes” below)

7. Specify the working directory

Click the “Select Directory” button to assign a working directory to the Agent. The Agent will have access to all files and subdirectories under this directory so it can understand the project context, read files, and execute code.

8. Set environment variables

  • Automatic configuration: Your selections in step 6 (model) and step 7 (working directory) will automatically generate the corresponding environment variables.

  • Custom addition: If your Agent or project requires other specific environment variables (for example PROXY_URL etc.), you can add them here manually.

9. Update options

  • Built-in executables: Cherry Studio has integrated the executables for all the above Code Agents for you, so in most cases you can use them directly without an internet connection.

  • Automatic updates: If you want the Agent to always stay up to date, you can check the option Check for updates and install the latest version . When checked, the program will connect to the internet at each startup to check and update the Agent tools.

10. Start the Agent

After all configurations are complete, click Start button. Cherry Studio will automatically invoke your system's Terminal and load all environment variables there, then run the Code Agent you selected. You can now interact with the AI Agent in the popped-up terminal window.


Important Notes

  1. Model compatibility notes:

    • Claude Code: Requires selecting a model that supports the Anthropic API Endpoint format. The officially supported models currently include:

      • Claude series models

      • DeepSeek V3.1 (official API platform)

      • Kimi K2 (official API platform)

      • Zhipu GLM 4.5 (official API platform)

      • Note: Currently many third-party providers (such as One API, New API, etc.) for DeepSeek, Kimi, and GLM often only support the OpenAI Chat Completions format, which may not be directly compatible with Claude Code and will require providers to gradually adapt.

    • Gemini CLI: Requires selecting Google's Gemini series models.

    • Qwen Code: Models that support the OpenAI Chat Completions API format. It is strongly recommended to use Qwen3 Coder series models for the best code generation results.

    • OpenAI Codex: Supports the GPT series models (such as gpt-4o, gpt-5 etc.).

  2. Dependency and environment conflicts:

    • Cherry Studio integrates an independent Node.js runtime environment, Code Agent executables, and environment variable configuration internally to provide a clean out-of-the-box environment.

    • If you encounter dependency conflicts or strange errors when starting the Agent, consider temporarilyuninstalling or disabling related dependencies installed on your system(such as globally installed Node.js or specific toolchains) to rule out conflicts.

  3. API Token consumption warning:

    • Code Agents consume API Tokens at a very high rate. When handling complex tasks, the Agent may generate a large number of requests to think, plan, and generate code, causing tokens to be consumed quickly.

    • Be sure to manage according to your API quota and budget,act within your means, and closely monitor token usage to prevent budget overruns.

We hope this tutorial helps you quickly get started with Cherry Studio's powerful Code Agent feature!

Last updated

Was this helpful?