GitHub Cool Projects Weekly Digest

Discover the tech stack behind any app on Google Play & App Store using Fork. Search apps based on technology usage and generate a tailored list of sales leads, with detailed company & contact info.

All-in-one UI for Exploring Merged LLMs on Hugging Face 🤗! Model merging is a cool new technique for creating powerful language models for cheap (no GPU required). MergeUI helps you answer questions like: which models to merge? what merge strategies to use?

If you're passionate about AI, join our 160+ AI Communities! Expand your knowledge and network with like-minded individuals in various free AI Communities. Share insights and learn valuable AI knowledge.

Curriculo is dedicated to revolutionizing the resume-building experience through the power of LLMs & prompt engineering. By offering editable PDFs, we ensure every individual has the opportunity to tailor their resume to perfection.

Effortlessly automate inbound and outbound calls with our AI voice agents – no coding needed. Empowering teams to handle tasks like appointment booking, customer care, and rescheduling, freeing them to focus on higher-value interactions.

CETI is a lightweight mind map software without the hassle of sign-ups or logins. All your data stays securely within your local browser storage. Powered by AI, CETI is engineered to expand your thinking capabilities and provide unparalleled insights.

Mebot acts as your second brain, designed to remember everything for you and enlighten you at any moment! This sophisticated digital 'you' helps you manage your thoughts, ideas, and documents efficiently, ensuring that nothing slips through the cracks.

ChatTTS is a voice generation model on GitHub at 2noise/chattts,Chat TTS is specifically designed for conversational scenarios. It is ideal for applications such as dialogue tasks for large language model assistants, as well as conversational audio and video introductions. The model supports both Chinese and English, demonstrating high quality and naturalness in speech synthesis. This level of performance is achieved through training on approximately 100,000 hours of Chinese and English data. Additionally, the project team plans to open-source a basic model trained with 40,000 hours of data, which will aid the academic and developer communities in further research and development.