Task and tab autocomplete
Continue will generate, refactor, and explain entire sections of code
Answer coding questions
Highlight sections of code and ask Continue for another perspective
- “what does this forRoot() static function do in nestjs?”
- “why is the first left join in this query necessary here?”
- “how do I run a performance benchmark on this rust binary?”
Edit in natural language
Highlight a section of code and instruct Continue to refactor it
- “/edit rewrite this to return a flattened list from a 3x3 matrix”
- “/edit refactor these into an angular flex layout on one line"
- “/edit define a type here for a list of lists of dictionaries”
Generate files from scratch
Open a blank file and let Continue start new Python scripts, React components, etc.
- “/edit get me started with a basic supabase edge function”
- “/edit implement a c++ shortest path algo in a concise way”
- “/edit create a docker compose file with php and mysql server"
Stay in flow when coding with LLMs
Continue acts natively inside your IDE, so you never have to switch windows, copy, and paste to get help from large language models ever again.
Choose any LLM
Use any model, including GPT-4, DeepSeek Coder, Claude 2, Code LLama, Gemini Pro, and more
Choose any provider
Deploy locally (Ollama, LM Studio, etc), in your cloud (vLLM, TGI, etc), or with SaaS (Together, OpenAI API, etc)
Your codebase as context
Ask Continue to automatically determine what context to use from your codebase or highlight it yourself
Local-first and modular
Use even when offline, bring your own vector database, and customize the experience exactly like you want it
Use your development data
Continuously finetune custom models using the data that your team collects as you build software with Continue
Deploy for your team
Reach out on Discord to get help setting up Continue once for your entire team to use together