This paper presents TTGL, a large-scale, multi-scenario universal graph learning framework developed at TikTok, which generates unified embeddings that capture diverse user interests across multiple contexts. TTGraph handles over 100 billion edges and 10 billion nodes daily, linking user behaviors from various scenarios such as video, search, live streaming and e-commerce. TTGL showcases a versatile strategy designed for handling large amounts of data and practical limitations, highlighting the balance between efficiency and precision in a high-volume production setting. TTGL utilizes a heterogeneous graph to unify user behaviors across different TikTok scenarios, dynamically learning shared embeddings that capture complex data patterns. It implements advanced domain-adaptive graph sampling and unsupervised training methods to handle its scale while ensuring fair representation. The graph embeddings are fed into online serving pipelines, delivering real-time recommendations that effectively balance efficiency and revenue generation. These effective graph online serving solutions are highly versatile, demonstrating their impact not only in TikTok's Feed video recommendations but also across various business scenarios such as e-commerce and live streaming. Through extensive offline evaluations and online A/B testing, we demonstrate that TTGL significantly improves key metrics across multiple contexts, achieving a 0.35% increase in 7-day retention, a 3.27% rise in watch live duration, a 1.32% boost in gross merchandise value, a 1.07% increase in paid order count, and a 1.0% improvement in search page views.