{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/f4c9e478af894ab5bb635eb7f36482bd\" frameborder=\"0\" width=\"1670\" height=\"1252\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1252,"width":1670,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1252,"thumbnail_width":1670,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/f4c9e478af894ab5bb635eb7f36482bd-1689799987409.gif","duration":207.536,"title":"Introducing RepoDog: An IDE AI Assistant with Repository Level Context","description":"Hey everyone, this is Dennis, and in this video, I'm going to introduce RepoDog, an AI assistant for IDEs that provides repository level context. RepoDog aims to understand your code base and answer sophisticated questions based on the code it retrieves. It focuses on context management, indexing your repository locally, and offering basic operations like code explanation and refactoring. RepoDog also respects .gitignore files and can perform tasks like rewriting code snippets in Python. In this video, I explain why I built RepoDog as an alternative to existing IDE extensions like code GPT and GitHub co-pilot chat, which have limited understanding of the entire repository. I'm looking to improve query compression and code base understanding through code tree and HD person. Feel free to test out RepoDog at repo.dog and provide feedback on the beta features."}