LAWGPT is a Chinese legal knowledge-enhanced large language model designed for legal applications. It addresses the limitations of existing open-source and proprietary models in legal tasks. Open-source models lack legal knowledge, while proprietary models do not ensure data privacy. LAWGPT incorporates legal-oriented pre-training and legal supervised fine-tuning to enhance its legal domain knowledge and performance on downstream tasks. The model is trained on a large-scale legal corpus and fine-tuned using a knowledge-driven instruction dataset. Experimental results show that LAWGPT outperforms the open-source LLaMA 7B model in major legal tasks. The model is open-source, allowing self-hosting and private access, ensuring data privacy. LAWGPT's contributions include the first open-source Chinese legal knowledge-enhanced large language model, a comprehensive legal pre-training corpus, a knowledge-driven instruction dataset, and demonstrating superior performance in legal tasks. The model is publicly available on GitHub and has received 5.7K stars. LAWGPT is designed to improve legal tasks such as legal judgment prediction, legal documents retrieval, and legal question answering. It is a significant advancement in the development of legal AI and provides a foundation for future research in Chinese legal applications.LAWGPT is a Chinese legal knowledge-enhanced large language model designed for legal applications. It addresses the limitations of existing open-source and proprietary models in legal tasks. Open-source models lack legal knowledge, while proprietary models do not ensure data privacy. LAWGPT incorporates legal-oriented pre-training and legal supervised fine-tuning to enhance its legal domain knowledge and performance on downstream tasks. The model is trained on a large-scale legal corpus and fine-tuned using a knowledge-driven instruction dataset. Experimental results show that LAWGPT outperforms the open-source LLaMA 7B model in major legal tasks. The model is open-source, allowing self-hosting and private access, ensuring data privacy. LAWGPT's contributions include the first open-source Chinese legal knowledge-enhanced large language model, a comprehensive legal pre-training corpus, a knowledge-driven instruction dataset, and demonstrating superior performance in legal tasks. The model is publicly available on GitHub and has received 5.7K stars. LAWGPT is designed to improve legal tasks such as legal judgment prediction, legal documents retrieval, and legal question answering. It is a significant advancement in the development of legal AI and provides a foundation for future research in Chinese legal applications.