This entry is compiled from primary sources: Continue.dev's official product documentation, release notes, and published licensing repositories.
It has not been hands-on tested by us. Where a limit, a price or a requirement is stated below, it is the published figure at the time of writing rather than a measured result.
Anything we have not verified is left out instead of guessed at.
Continue.dev Review (2026) — Open Source AI Assistant for VS Code & JetBrains
Apache 2.0 Open SourceIDE ExtensionContinue Dev Inc.
Continue.dev is a leading open-source AI code assistant extension for Visual Studio Code and JetBrains IDEs. Built under the Apache 2.0 licence, Continue acts as a modular AI layer that connects any LLM—whether running locally on your hardware via Ollama or remotely via cloud API keys—directly into your editor.
Because Continue is 100% open-source software, there are no artificial trial periods, no tier restrictions, and no account requirements for individual developers.
What you get with Continue.dev (100% Free Software)
Continue installs directly from the VS Code Marketplace or JetBrains Marketplace with zero cost. Core features include:
- 100% Local & Private AI Coding: Connect to Ollama, LM Studio, or vLLM to run models like Starcoder 2, DeepSeek Coder, or Qwen 2.5 Coder 100% offline with zero data telemetry.
- Custom API Backend Choice: Plug in your own API keys for Anthropic (Claude 3.5 Sonnet), OpenAI (GPT-4o), Together AI, or Groq to pay strictly for raw model API tokens.
- IDE Side-Panel Chat & Inline Edit: Highlight code blocks and press
Cmd+I/Ctrl+Ito request inline refactoring, or chat with your codebase in the side panel. - Rich Context Indexing (
@Files,@Docs,@Codebase): Reference specific repository files, documentation URLs, or git diffs directly inside your prompt prompts. - Multi-IDE Support: Works identically across VS Code and JetBrains (IntelliJ IDEA, PyCharm, WebStorm, Android Studio).
Understanding Continue.dev's operational costs
The Continue extension itself is completely free. Infrastructure choices dictate costs:
- Local Models (Ollama): $0/month forever. Requires a GPU with sufficient VRAM for low-latency code completion.
- Cloud LLM APIs (Anthropic / OpenAI / DeepSeek): Pay per token directly to your model provider. Using budget providers like DeepSeek or Groq keeps monthly AI spending well under $2/month for most developers.
Pros
- 100% free and open-source extension (Apache 2.0) with zero vendor lock-in.
- Complete privacy mode when connected to local Ollama model instances.
- Modular architecture allows effortless switching between local models and commercial cloud APIs.
- Cross-platform support for both VS Code and the full JetBrains IDE suite.
Cons
- Requires initial JSON configuration setup to connect your preferred LLM provider.
- Cloud model completions require maintaining your own API keys and provider billing.
- Autocomplete speed with local LLMs depends heavily on local workstation GPU power.
Best alternatives
- Aider — Open-source CLI-based AI pair programmer with automatic Git commits (code).
- Codeium — Free hosted IDE extension providing out-of-the-box autocomplete without model configuration (code).
- Cursor — AI-first editor fork of VS Code with integrated model hosting (code).
FAQ
Is Continue.dev completely free to use? Yes. The Continue extension for VS Code and JetBrains is 100% free and open source under the Apache 2.0 licence.
Can I run Continue.dev completely offline with local models? Yes. Continue seamlessly connects to Ollama, LM Studio, or local inference servers, keeping all code and prompts on your local machine.
What IDEs does Continue.dev support? Continue supports both Visual Studio Code and JetBrains IDEs (including IntelliJ IDEA, PyCharm, WebStorm, and Android Studio).