VisualGDB includes a fast AI editing engine, specifically designed for C/C++ projects where the full context is spread between multiple large files.

You can initiate an AI edit by clicking the edit link next to the CodeJumps annotation on top of a symbol. VisualGDB will automatically find and attach definitions of relevant symbols to your request:
This allows editing code on a much higher level. Instead of manually changing several declarations, you can point VisualGDB to the relevant symbol, give a brief description what to do, and the AI will get it right in most of the cases:

Edits typically take 2-10 seconds, and can be easily stepped back or retried. So, you can give very brief instructions, see if the AI gets it right from the first time, and retry the step, or give quick follow-up instructions:

Supported Models

VisualGDB supports any language model capable of completing chats. You can use any cloud service of your choice, or even run the models on your own hardware. You can configure models via Tools->VisualGDB->Manage AI models:VisualGDB provides a limited number of evaluation tokens for common models. For production use, we recommend creating an account at OpenRouter that provides access to state-of-the-art models from all major vendors. You can also get limited free tokens from Cerebras Cloud or any other model provider with OpenAI-style API.