SuperAPI AI Directory
Partner with us中文AI newsFavorites
All toolsAI codingVisual Studio Marketplace

Visual Studio Marketplace

Custom Pilot is a Visual Studio Code extension framework for integrating custom code completion models into VS Code. It supports any API server that follows the OpenAI API format, especially services that provide a POST /v1/completions endpoint. Users can set the API server URL in the extension's sidebar panel, select an inference model from a dropdown menu, and enter an API Key when the API requires authentication (the Key will be sent with the Authorization header with each request). Users can also adjust advanced settings as needed. The selected model will provide code completion for any programming language and any file. The extension also supports working with LM Studio, thereby running LLM locally offline and integrating it into VS Code.

Open website

About this tool

Custom Pilot is a Visual Studio Code extension framework designed to make it easy for users to integrate custom code completion models into VS Code.

Purpose

The extension is used to use custom code completion models within VS Code to provide completion suggestions for any programming language and any file.

Main capabilities

  • Supports any API server that follows the OpenAI API format, especially one that needs to provide a POST /v1/completions endpoint.
  • Configure the API server URL in the extension's sidebar panel.
  • Select an inference model from a dropdown menu.
  • If the API requires authentication, enter an API Key, and the key will be sent with the Authorization header with each request.
  • Advanced settings can be adjusted.
  • The selected model will provide code completion for any programming language and any file.
  • Can work with LM Studio to integrate a locally running LLM model into VS Code, enabling offline operation.

Usage

  1. Install the Custom Pilot extension in VS Code.
  2. Open the extension's sidebar panel to configure it:
    • Set the API server URL.
    • Select an inference model from the dropdown menu.
    • If the API requires authentication, enter the API Key (it will be sent with the Authorization header with each request).
    • Optionally adjust advanced settings.
  3. After configuration is complete, the selected model will provide code completion for any programming language and any file.

Steps to use LM Studio:

  • First, follow the guide to run a local web server in LM Studio.
  • Then, in the Custom Pilot sidebar panel, set the API server URL to http://<ip_address>:1234, where <ip_address> is the IP address of the machine running LM Studio. For example, if LM Studio is running on the local machine, the URL can be set to http://localhost:1234。
  • Select an inference model from the dropdown menu to use that LLM model in VS Code.

Applicable scenarios

  • Developers who want to use custom code completion models in VS Code.
  • Users who want to integrate an API server that follows the OpenAI API format.
  • Users who want to run LLM locally offline and integrate it into VS Code (through LM Studio).
  • Suitable for code completion needs in any programming language and any file.

Limitations

The materials do not provide specific information about fees, pricing, platform compatibility, performance guarantees, installation commands, etc.

Related tools

Browse category