Continue
This tool is no longer in active use. Observations from evaluation through 2024 and 2025.
Overview
Continue is an open-source AI code assistant that integrates with VS Code and JetBrains. It provides inline code suggestions, chat-based assistance, and custom slash commands. Unlike standalone CLI agents, it operates within the editor and can be configured to use various LLM backends, including local models.
Review context
Strengths
- Fully open source under Apache 2.0 license. Code can be inspected and modified.
- Flexible model backend support, including local models for privacy-sensitive work.
- Custom slash commands allow creating reusable workflows for common tasks.
- Active community with a growing plugin ecosystem.
Limitations
- Requires an IDE. Not a standalone CLI agent for headless or remote use.
- Context understanding is limited to open files and project index, reducing awareness compared to CLI agents with full filesystem access.
- Setup is more complex than commercial alternatives, particularly for custom model configurations.
- Occasional instability when switching models during a session.
Where it fits
Continue fills a specific niche as a privacy-respecting, IDE-integrated code assistant with flexible model backends. It is best suited for teams that need to self-host or use custom model deployments, and for developers who want AI assistance within the editor rather than through a separate interface.
Current assessment
Continue is a well-designed open-source tool for in-editor AI assistance. Its strength is flexibility and privacy, not autonomous capability. It serves a complementary role to CLI agents rather than replacing them.
Reference
Revision history
2026-07 Rewritten.
2026-06 Published.