YouTube ranks among the most visited websites globally with 2.6 billion users. Every minute an average 500 h of video content are uploaded with most of these receiving the comments. These comments serve as valuable sources of data for YouTubers. Engaging with an audience is essential for YouTubers who seek to build a loyal community and improve viewership. To tackle these challenges a web app is developed on Streamlit framework and deployed on Streamlit Share. This web app supports features like Comment Sentiment Analysis, Automatic reply, Comment ChatBot, and Transcript Summarizer. Youtubers can access this deployed web app and enter their YouTube Uniform Resource Locator (URL). Later in the backend YouTube Data Application Programming Interface (API) V3 scrapes the comments from the entered url.pandas_profiling and streamlit_pandas_profiling modules are used as part of EDA. On these extracted comments, various Natural Language Processing (NLP) techniques such as lowercasing, tokenization, stopword removal, and lemmatization are applied. On the cleaned-up comments, TextBlob Sentiment Analysis is used to get the polarity of each comment. The YouTube Transcript API is used to extract transcripts from videos and utilized as input for the Cohere model summarize-xlarge variant to generate summaries. It is also utilized in a Retrieval-Augmented Generation (RAG) process alongside the latest comments for the Automatic Comment Reply feature. In the Comment Chatbot, both the user queries and comments serve as input, with text embedding applied to both. The similarity index between both is calculated using cosine similarity, and comments with a cosine value greater than 0.1 are included in the query output.