IDE

Continue.dev

Continue.dev, role by role.

Open-source IDE assistant with role-based routing. Point chat, edit, autocomplete, and embed at Melious, separate models for each. Agent mode reuses the chat model.

Get your API key Visit Continue.dev
~/.continue/config.yaml
name: Local Assistant
version: 1.0.0
schema: v1

models:
  - &melious
    name: Melious · Chat
    provider: openai
    apiKey: sk-mel-<YOUR_API_KEY>
    apiBase: https://api.melious.ai/v1
    model: glm-5.1
    roles: [chat, edit, apply]

  - <<: *melious
    name: Melious · Autocomplete
    model: glm-5.1
    roles: [autocomplete]
About

What is Continue.dev?

Continue is an open-source AI assistant for VS Code, JetBrains, and Neovim. Chat sidebar, inline edits, code apply, autocomplete, codebase-wide retrieval, and an agent mode that plans and runs multi-step edits inside the IDE. The interesting part is the role-based config: each model entry picks up one or more of chat, edit, apply, autocomplete, embed, summarize. A small fast model handles keystrokes, a stronger one handles the sidebar and agent runs. All of it through a plain YAML file with first-class OpenAI-compatible provider support.

Visit the official site continue.dev
Setup

How to use Continue.dev with Melious?

  1. Install the extension

    Search Continue in your IDE marketplace and install. The config file gets created on first launch: ~/.continue/config.yaml on macOS/Linux, %USERPROFILE%\.continue\config.yaml on Windows.

  2. Drop in the Melious config

    Open the config file and paste in the blocks below. Required header keys (name, version, schema) come first. After that, one model entry per role. Use one strong chat/edit model and one fast autocomplete model. Splitting them is the whole point of Continue.

    ~/.continue/config.yaml
    name: Local Assistant
version: 1.0.0
schema: v1

models:
  - &melious
    name: Melious · Chat
    provider: openai
    apiKey: sk-mel-<YOUR_API_KEY>
    apiBase: https://api.melious.ai/v1
    model: glm-5.1
    roles: [chat, edit, apply]

  - <<: *melious
    name: Melious · Autocomplete
    model: glm-5.1
    roles: [autocomplete]

  - <<: *melious
    name: Melious · BGE M3
    model: bge-m3
    roles: [embed]

  3. Save and use

    Open the chat sidebar, your Melious models appear in the dropdown. Continue normally hot-reloads on save; if it doesn't, run Continue: Reload Window from the command palette. Embedding indexes start running in the background.

Ready?

Three steps from here.

Grab a Melious key. Pick your tool. Follow the guide. Same client, now answering from Europe.

Get your API key Browse all integrations