Continue (Open-Source AI Coding)

Self-hostable VS Code/JetBrains extension with configurable models, context providers, and tools.

AI Coding ToolsIntermediate

Why

Stack Overflow's 2024 survey found 62% of developers currently use AI tools (up from 44% in 2023), with 82% of them using AI to write code. Continue is fully open-source and config-driven (config.yaml).

You can point it at local Ollama, a private OpenAI-compatible gateway, or cloud models, and add custom context providers (docs, codebase, web). This makes it the go-to when data residency or vendor lock-in matters.

When

Pick Continue when you need on-prem models, custom retrieval over your docs, or a single config your whole team commits. Skip it if you want a polished out-of-box experience like Cursor.

How

1. Install the "Continue" extension. 2. Edit ~/.continue/config.yaml (or .continue/config.yaml in the repo). 3. Define models: list providers (openai, anthropic, ollama) with apiBase + apiKey. 4. Define context providers: codebase, docs (folder), github, search. 5. Use Cmd+I (inline edit) and Cmd+L (chat); @-mention providers for context. 6. Slash commands in config let you build reusable prompts (e.g., /explain, /test).

Example

# .continue/config.yaml models: - name: Local Llama provider: ollama model: llama3.1:8b - name: Sonnet provider: anthropic model: claude-3-5-sonnet contextProviders: - provider: codebase - provider: docs params: { folders: ["./docs"] } slashCommands: - name: test description: generate tests for current file prompt: "write vitest tests for {{input}}"

Common Problems

⚠Error: Cannot find module 'xxx' → run `npm install xxx` and restart the editor/extension host.
⚠Error: "Extension not activated" / greyed-out AI features → check the API key setting and network; run the extension's "Check Connection" command.
⚠Error: Rate limit 429 → upgrade plan or reduce request frequency; check the tool's usage dashboard for quota.

Best Practices

✓Commit .continue/config.yaml to share models, providers, and slash commands.
✓Use the codebase provider with @codebase for project-aware answers.
✓Measure the outcome with a concrete metric (time saved, defect rate, test coverage) so the practice can be justified and improved.

FAQ

What is Continue (Open-Source AI Coding)?

Self-hostable VS Code/JetBrains extension with configurable models, context providers, and tools. It helps developers quickly grasp the core value and use cases of Continue (Open-Source AI Coding).

How do I get started with Continue (Open-Source AI Coding)?

To get started with Continue (Open-Source AI Coding), focus on these points first: Install the "Continue" extension.

What are common mistakes with Continue (Open-Source AI Coding)?

Common mistakes when using Continue (Open-Source AI Coding) include: Error: Cannot find module 'xxx' → run `npm install xxx` and restart the editor/extension host.; Error: "Extension not activated" / greyed-out AI features → check the API key setting and network; run the extension's "Check Connection" command.; Error: Rate limit 429 → upgrade plan or reduce request frequency; check the tool's usage dashboard for quota..

What are the best practices for Continue (Open-Source AI Coding)?

Best practices for Continue (Open-Source AI Coding) include: Commit .continue/config.yaml to share models, providers, and slash commands.; Use the codebase provider with @codebase for project-aware answers.; Measure the outcome with a concrete metric (time saved, defect rate, test coverage) so the practice can be justified and improved..

How do I learn more about Continue (Open-Source AI Coding)?

Start with the official docs, then search real-world examples on GitHub. Validate patterns in a small scratch repo before applying them to production code.