GitHub Copilot Privado e Gratuito: Como Usar o Continue.dev no VS Code com Modelos Locais
Assinaturas recorrentes de assistentes de IA (como GitHub Copilot, Cursor e Supermaven) pesam no bolso do desenvolvedor e representam um pesadelo de compliance para empresas que lidam com código confidencial, segredos industriais e exigências de LGPD/GDPR. Com os saltos recentes nos modelos de código de pesos abertos — em especial a família Qwen 2.5 Coder da Alibaba Cloud —, agora é possível ter…
The article explains how to set up a local, free AI coding assistant, called Continue.dev, within the VS Code code editor using local models. The main benefits include eliminating recurring subscription costs and ensuring all code remains within a private network. Two models are highlighted: Qwen 2.5 Coder 7B for contextual chat and test generation, and Qwen 2.5 Coder 1.5B as an autocomplete model.
The setup process involves pulling these models using Ollama, configuring the Continue.dev extension in VS Code, and utilizing keyboard shortcuts for inline autocompletion, lateral chat, and refactoring. The author emphasizes the advantages of running AI locally, such as no internet dependency and secure code storage.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
This story
This is one outlet's version. Read the fullest account.
