Continue
✓ VerifiedOpen-source, model-agnostic AI coding assistant for VS Code and JetBrains
Our Review
Continue is an open-source VS Code and JetBrains extension for AI-assisted coding. It supports local models (Ollama, llama.cpp) and cloud providers (OpenAI, Anthropic, Gemini, DeepSeek) via your own API keys. There is no subscription for the extension; you pay only for external API usage if you choose cloud models.
We tested Continue with both local and cloud setups. For privacy-sensitive work, running Ollama locally gives you completions and chat without sending code off-device. For more capable models, connecting OpenAI or Anthropic keys is straightforward. The interface is familiar if you have used Copilot or Cursor Tab: inline completions, a chat panel, and codebase context.
Continue is ideal for developers who want open-source tooling, local model support, or maximum control over model choice and spend. It does not offer the same level of agentic multi-file automation as Cursor or Aider, but for daily autocomplete and chat it is solid. Teams that need SSO or central billing will need to look at commercial offerings.
Review updated December 6, 2025.
About
Continue is an open-source coding assistant that lets developers use their own models (OpenAI, Anthropic, local via Ollama/LM Studio) with custom prompts and workflows. It runs as a VS Code and JetBrains extension, supports chat and completions, and can be self-hosted or run fully local for privacy.
Key Features
- ✓Model-agnostic with BYO keys
- ✓Open-source and customizable prompts/commands
- ✓Local/offline support via Ollama or LM Studio
- ✓Context providers for codebase awareness
- ✓Chat, completions, and slash commands
- ✓Self-host or run fully locally for privacy
Pros & Cons
Pros
- Open-source and model-agnostic with BYO API keys
- Local/offline support via Ollama or LM Studio
- VS Code and JetBrains extensions; zero data retention
Cons
- No agentic mode
- No built-in codebase indexing
Use Cases
- →Privacy-focused development with local models
- →Custom AI workflows with personalized prompts
- →Self-hosted AI coding for enterprises
- →Offline development with local LLMs
- →Experimenting with different AI models
- →Open-source projects and contributions
Technical Details
Languages
AI Models
Integrations
Get Continue Updates
Be the first to know when Continue changes pricing, adds features, or offers deals.
No spam, unsubscribe anytime.
Frequently Asked Questions
What is Continue?
Continue is an open-source coding assistant that lets developers use their own models (OpenAI, Anthropic, local via Ollama/LM Studio) with custom prompts and workflows. It runs as a VS Code and JetBrains extension, supports chat and completions, and can be self-hosted or run fully local for privacy.
Is Continue free?
Yes, Continue is open source and free to use. VS Code and JetBrains extensions, Chat and code completions, Custom prompts and slash commands
What programming languages does Continue support?
Continue supports 1+ programming languages including All languages supported by chosen model.
What AI models does Continue use?
Continue is powered by Any LLM via API, OpenAI, Anthropic, Gemini, Local (Ollama/LM Studio), Custom endpoints.
What platforms does Continue support?
Continue is available on macOS, Linux, Windows.
What can Continue do?
Continue provides code completion, code generation, debugging, AI chat. Key features include: Model-agnostic with BYO keys, Open-source and customizable prompts/commands, Local/offline support via Ollama or LM Studio.
Related Articles
OpenAI Codex mid-May 2026 updates: Appshots, Goal Mode GA, and Codex CLI 0.131 → 0.133
Between May 18 and May 21, 2026, OpenAI shipped Codex CLI 0.131.0, 0.132.0, and 0.133.0 plus the 26.519 app release introducing Appshots, Goal Mode as standard, remote computer use, and plugin sharing for Business.
Claude Code 2.1.139 (May 2026): new agent view + /goal command
Claude Code 2.1.139 adds an agent view (claude agents) and a new /goal command, plus a long list of MCP, plugin, hooks, and reliability improvements.
Warp Goes Open Source (April 28, 2026): AGPL Client, OpenAI as Founding Sponsor, Oz-Driven Contributions
Warp open-sourced the Warp client under AGPL on April 28, 2026 at github.com/warpdotdev/warp, with OpenAI as the founding sponsor, expanded support for Kimi/MiniMax/Qwen plus an 'auto (open)' router, and a new Oz-agent-driven contribution workflow. (updated with changelog-confirmed TOML settings + /feedback details)
Workflow Resources
Pricing and features change frequently—confirm on the vendor site.
We may earn a commission if you sign up. See our disclosure.
Pricing
Free (Open Source)
$0
- VS Code and JetBrains extensions
- Chat and code completions
- Custom prompts and slash commands
- Local/self-hosted model support (Ollama, LM Studio)
- BYO API keys for hosted models
Company
- Name
- Continue (open source)
- Founded
- 2023
- Location
Links
Similar Tools
Compare Continue with these alternatives
Continue
Open Source