Continue Public

Continue for AI Engineer brings chat, inline edits, autocomplete, and coding agents into the editor so you can stay in the same workflow while working with AI models.

Continue is available for various IDEs. The following IDEs are currently supported:

• Visual Studio Code
• JetBrains.

Key Features

• Chat interface for questions, code explanations, and development assistance
• Inline edits for targeted code changes without leaving the file
• Autocomplete for low-latency code suggestions while you type
• Coding agents for multi-step tasks such as reading files, running commands, and applying changes

Usage Guidelines

Please Read Before Installation

• Continue is a custom version of the plugin for enterprise usecases with no telemetry. This custom version has telemetry and communication to third-party providers disabled, and some features have been improved for enterprise-compliant usage.
• Please carefully review all AI-generated content before using or sharing it. Do so in the same manner as you would with your manual work (using peer reviews, the four-eyes principle, etc.). The AI components of AIFS can make mistakes.
• Do not enter any personal data.
• If you have further questions about the AI components of AIFS, please refer to the corresponding documentation. For additional questions or suggestions, please contact AI Engineer Support team.
• Use the assistant exclusively for your professional inquiries.
• The entered data will not be used for training the large language models.
• The assistant usually works quickly, but it may take some time for complex inquiries or document searches. Please be patient and wait for the assistant’s complete response.
• AI models like ChatGPT are generative models, meaning they generate text without explicitly verifiable facts. This can result in the assistant providing plausible but not necessarily correct information.
• Deployment of AI Engineer in high-risk areas Annex III AIA or for customers in regulated sectors Annex I AIA is not allowed.

Installation

Continue is currently available for Visual Studio Code and JetBrains.

Visual Studio Code

AIFS

1. Download the Continue extension from AI Coding Plugins.
2. If you are updating an existing installation, delete the old Continue extension folder from .vscode/extensions.
3. In VS Code, open Extensions, open the three-dot menu, and choose Install from VSIX.
4. Select the downloaded plugin file and reload Visual Studio Code.

Strive

1. Download the Continue extension from AI Coding Plugins.
2. If you are updating an existing installation, delete the old Continue extension folder from .vscode/extensions.
3. In VS Code, open Extensions, open the three-dot menu, and choose Install from VSIX.
4. Select the downloaded plugin file and reload Visual Studio Code.

JetBrains

AIFS

1. Open Settings in your JetBrains IDE and select Plugins.
2. On the Plugins page, click the settings icon and choose Manage Plugin Repositories.
3. In the Custom Plugin Repositories dialog, add the repository URL from AI Coding Plugins
4. Click OK to save the repository list and apply the changes.
5. Open Marketplace, search for Continue for AI Engineer, and install it.

Strive

1. Open Settings in your JetBrains IDE and select Plugins.
2. On the Plugins page, click the settings icon and choose Manage Plugin Repositories.
3. In the Custom Plugin Repositories dialog, add the repository URL from AI Coding Plugins
4. Click OK to save the repository list and apply the changes.
5. Open Marketplace, search for Continue for AI Engineer, and install it.

Config File Setup

After the first installation, open the AI Engineer Continue plugin and choose Local config. This opens an empty config.yaml file. The config file defines the available AI models and how they connect to the LLM service. The file is written in YAML format, so indentation is important. Always use spaces instead of tabs.

General Structure

name: Local Config
version: 1.0.0
schema: v1
models:
  - ...

Top-Level Fields

Field	Description
name	The name of the configuration. Choose any descriptive name.
version	The version of the configuration file. Update this only when maintaining different configuration versions.
schema	The configuration schema version. This should normally remain v1.
models	A list of AI model configurations.

Adding a Model

Each model is defined as an entry under the models section.

Example:

- name: gpt-4.1
  model: gpt-4.1
  provider: openai
  apiBase: https://llm-server.llmhub.t-systems.net/v2/coding
  apiKey: ${{ secrets.OPENAI_API_KEY }}
  roles:
    - chat

Model Fields

Field	Description
name	A human-readable name for the model. This name is displayed to users and can be any descriptive label.
model	The model identifier expected by the server. The value must exactly match the deployed model name.
provider	Specifies the API provider used to access the model. For this configuration, use openai.
apiBase	The base URL of the LLM API endpoint. E.g. https://llm-server.llmhub.t-systems.net/v2/coding if you like to purchase models from AIFS.
apiKey	The API key used for authentication. It is recommended to reference a secret (for example, ${{ secrets.OPENAI_API_KEY }}) instead of hardcoding the key.
roles	Defines the capabilities supported by the model. A model can support one or more roles such as chat, edit, and apply.

Example config.yaml

name: Local Config
version: 1.0.0
schema: v1
models:
  - name: gpt-4.1
    model: gpt-4.1
    provider: openai
    apiBase: https://llm-server.llmhub.t-systems.net/v2/coding
    apiKey: ${{ secrets.OPENAI_API_KEY }}
    roles:
      - chat
  - name: Qwen3-30B-A3B-FP8
    model: Qwen3-30B-A3B-FP8
    provider: openai
    apiBase: https://llm-server.llmhub.t-systems.net/v2/coding
    apiKey: ${{ secrets.OPENAI_API_KEY }}
    roles:
      - chat
      - edit
      - apply

Windows only

If you use IntelliJ or PyCharm on Windows, add your proxy settings to the configuration file:

requestOptions:
  proxy: YourProxyHost:Port

Once the config is saved, you can start a chat and use Continue.

Using an environment variable

The ${{ secrets.OPENAI_API_KEY }} reference resolves the value at runtime instead of pinning the API key into your config.yaml. Continue searches the following sources in order:

1. A .env file in your workspace root
2. .continue/.env in your workspace
3. ~/.continue/.env in your home directory
4. The process environment

Visual Studio Code may not see your shell environment

On macOS and Windows, Visual Studio Code typically does not inherit shell environment variables. Even if you exported OPENAI_API_KEY in your terminal during the Quickstart, Continue running inside Visual Studio Code may not see it. The reliable path is a .env file.

Updating

Automatic updated are included for Continue whenever a new version is published.

Visual Studio Code

When you start or reload Visual Studio Code and an update is available, a popup appears.

1. Click Update Now to download the latest version.

2. After the download completes, click Reload Window.

After Visual Studio Code restarts, the latest Continue version is ready to use.

JetBrains

When you start or reload JetBrains and an update is available, a popup appears.

You can also check manually in Settings -> Appearance & Behavior -> System Settings -> Updates.