Continue
Screenshots
The Story
Continue is an AI coding assistant that installs into VS Code and JetBrains IDEs. Unlike assistants tied to one vendor's model, it is configured with a model provider, so it can point at a hosted API, a local runtime, or an internal endpoint.
The feature set covers the common assistant interactions: inline autocomplete as you type, a chat panel that can see the open file, and edit commands that apply a change across a selection. Context providers decide what the model sees, which is how a question can include the current file, an open diff, or a documentation source.
The project is open source, and configuration lives in a file in the repository, so a team can share a setup. The tradeoff is that the assistant is only as good as the model behind it: a local model avoids sending code away but performs below a frontier hosted model, and the team has to make that trade explicitly.
Overview
Continue's distinguishing choice is that the model is configuration rather than the product, so the same assistant can run against a hosted API or a local runtime.
The extension installs into VS Code and JetBrains IDEs and provides the interactions an assistant is expected to have: autocomplete as you type, a chat panel that can see the open file, and edit commands applied across a selection. What differs is where the completions come from.
Model providers are configured in a file, and a provider can be a hosted API, a local runtime such as Ollama, or an internal endpoint. Because the configuration lives in the repository, a team can share a setup and standardise on one provider without each developer configuring their own.
Context providers decide what the model can see. A question can include the current file, an open diff, a documentation source, or a retrieved set of files. The tradeoff is the model: a local model keeps code on the machine but performs below a frontier hosted model, and that decision is left explicitly to the team.
Key Features
- Configurable model providers
Hosted APIs, local runtimes, and internal endpoints can all back the assistant, chosen in a repository config file.
- Inline autocomplete
Suggestions appear as you type, which is the interaction used most often during editing.
- Context providers
The model can be given the current file, an open diff, or a documentation source depending on the question.
- Open source
The extension is open source, so the assistant can be inspected and run against infrastructure you control.
Where Continue is a strong choice, and where it is not
Choose Continue when the team wants an editor assistant whose model provider is a configuration choice, including a local model when code cannot be sent to a third party.
Look elsewhere if the priority is the strongest available completion quality and the team is willing to accept a single vendor's hosted model to get it.
Getting started
The extension installs in minutes; choosing a model provider is the decision.
- ~10 minTime to first completion
Install the extension and it works with a default provider. Configuration is a file in the repository.
- FreeCost to start
The extension is open source. Model usage is billed by whichever provider you configure.
- An editorPrerequisites
VS Code or a JetBrains IDE, plus a model provider or a local runtime.
Known limitations
Constraints confirmed from the project's documentation.
- Quality follows the model. A local model keeps code on the machine and performs below a frontier hosted model.
- Configuration is file-based. That is shareable across a team and less approachable than a settings UI.
- Fewer features than a vendor-integrated assistant. The editor and assistant are separate products.
- Context is limited by what you attach. The assistant sees what the context providers give it, not the whole project by default.
Pick Continue when the model should be your choice
The assistant is a configuration layer, so the same tool can run against a hosted API, a local runtime, or an internal endpoint.
That flexibility is the differentiator, and it matters most when code cannot be sent to a third party.
If you want the strongest completion quality and accept a single vendor's hosted model, a vendor-integrated assistant is ahead.
FAQ
What is Continue?
Continue is an open-source AI coding assistant that installs into VS Code and JetBrains IDEs and can use a hosted or local model.
Is Continue free?
The extension is open source and free. Model usage is billed by whichever provider you configure.
Can Continue use a local model?
Yes. It can point at a local runtime such as Ollama, which keeps code on the machine.
Which editors are supported?
VS Code and JetBrains IDEs.
What stack is Continue built with?
CompassPad records Continue as a TypeScript extension with a Python core, based on its public repository.
What we checked
- LIVESite and primary link
The marketing site resolved and the primary product link reached the application.
- PRICINGPricing page
The extension is open source and free to use; there is no paid pricing page for the software.
- DOCSDocumentation
Documentation is public and covers model providers, context providers, and editor setup.
- FRESHNESSChangelog
A dated public blog publishes releases and is reachable without an account.
Discussion
No comments yet. Be the first.
Join the conversation. Sign up to comment.
Sign up free