Continue.dev

Continue.dev is an open-source AI code assistant that brings your favorite LLM into VS Code and JetBrains for agentic coding and context-based chat.

/images/agents/icons/continue.png
8.5
Shipyard Score
Excellent

What is it?

Continue.dev is an open-source AI code assistant that brings an extensible GitHub Copilot-style UX to VS Code and JetBrains. Essentially, it’s an LLM interface that connects your preferred model to your IDE, and gives you tooling to utilize that LLM via agents or context-based chat.

Continue.dev VS Code extension interface showing AI-powered code completion and chat assistance for developers Continue.dev agent in VS Code editing files

What can I use it for?

We appreciate that Continue has all the perks of GitHub Copilot but with more flexibility/extensibility, and being entirely OSS. There are a few different “modes” that it has, and its performance varies strongly on which LLM you plug in.

  • Code completion: Finish your functions/API calls with the correct syntax + logic
  • Codebase chat: Ask questions about your code and get info/feedback customized to your particular setup
  • Refactoring assistance: Get suggestions for improving code structure and patterns
  • Debugging: Puzzle out bugs step-by-step in chat or agent mode
  • Documentation: Automate doc generation with the context of a new feature
  • Custom model integration: Use different AI models for different results

What we like about it

We like how customizable Continue is. It adapts to natural dev workflows and can be used in different ways for different development styles. If you like Copilot, you’ll probably find Continue has a better UX and is more intuitive.

Our biggest feedback to potential users: since Continue uses your existing LLM subscription, you’ll want to research how to best utilize that LLM for your desired dev tasks. The output quality depends heavily on which model you choose to use, so you’ll want to understand your LLM and prompt accordingly.

Continue.dev AI code assistant performing code refactoring and analysis with customizable model integration Continue.dev chat mode with refactoring suggestions based on current context

Try Shipyard today

Get isolated, full-stack ephemeral environments on every PR.

Shipyard's Agentic Corner

Get better agentic workflows by instantly deploying to ephemeral environments.

Shipyard's environments are agent-friendly, so you can have a more continuous and productive agentic dev loop.

Stay connected

Latest Agents

Shipyard Newsletter
Stay in the (inner) loop

Hear about the latest and greatest in cloud native, container orchestration, DevOps, and more when you sign up for our monthly newsletter.