Show HN: Continue – Open-source coding autopilot

Continue is an open-source coding autopilot for VS Code that replaces manual ChatGPT copy-pasting with an integrated LLM assistant. It emphasizes transparency, hackability, and user control by supporting any LLM (local or cloud), collecting development data locally, and offering extensive customization through slash commands, context sources, and policies. The platform enables developers to maintain privacy while leveraging AI assistance and automatically gather data to improve their own LLM models.

Key Points

• •Replace ChatGPT copy-pasting workflow with integrated sidebar prompting and streamed edits directly in VS Code editor
• •Support any LLM including local models (ggml), open-source alternatives, or proprietary APIs (OpenAI, Anthropic) for maximum flexibility and privacy
• •Manage context intelligently using @-mentions for GitHub issues, files, Google searches, and other custom context sources
• •Extend functionality with custom slash commands (/commit, /docs, /ticket), context sources, system message templates, tools, and goal-oriented agent policies
• •Automatically collect development data locally in `.continue/dev_data` to create a feedback loop for improving team-specific LLM models
• •Maintain 100% privacy by running local models or hosting on private infrastructure instead of sending code to third-party services
• •Enable write-code-run-code-read-errors-fix-code loops through customizable policies and tool integrations
• •Provide transparency into LLM decision-making and context usage, addressing the black-box nature of existing developer tools
• •Monetize through paid development data engine for organizations seeking continuous feedback loops and fresh model training

Workflow Diagram

Concepts