For the complete documentation index, see llms.txt. Markdown versions of all docs pages are available by appending .md to any docs URL.
VS Code Continue
Configure Continue extension for VS Code to use agentgateway
Configure Continue, the open-source AI code assistant for VS Code, to route requests through agentgateway.
Before you begin
- Install the
agentgatewaybinary. - Install VS Code with the Continue extension.
Example agentgateway configuration
# yaml-language-server: $schema=https://agentgateway.dev/schema/config
llm:
port: 3000
models:
- name: "*"
provider: openAI
params:
apiKey: "$OPENAI_API_KEY"Configure Continue
- Edit the
~/.continue/config.yamlfile to add your agentgateway endpoint. If the file already has amodelslist, add the model to that list. - Save the file and reload Continue in VS Code.
name: agentgateway
version: 0.0.1
schema: v1
models:
- name: agentgateway
provider: openai
model: gpt-4o-mini
apiBase: http://localhost:3000/v1Review the following table to understand this configuration.
| Field | Description |
|---|---|
name | At the top level, a name for the configuration. In the models list, the display name shown in the Continue model selector. |
version, schema | Required by the Continue config.yaml format. Keep schema: v1. |
provider | Set to openai for any OpenAI-compatible endpoint. |
model | The model name from your agentgateway backend configuration. |
apiBase | Your agentgateway URL with the /v1 path. |
Verify the connection
- Open the Continue sidebar in VS Code (
Cmd + Lon macOS,Ctrl + Lon Windows/Linux). - Select agentgateway from the model dropdown.
- Send a test message: “Hello, are you working?”