XLang: An Open-Source Framework for Building Language Model Agents via Executable Language Grounding
- [2023, Aug 8] We've released XLang Agent demos, including Data, Plugins, and Web agents! Check tutorials and use cases!
We are pushing forward to open-source our framework, models, demos, code, benchmarks, and beyond. Please stay tuned! 🚀🚀
We built three real-world agents with chat-based web UI (check XLang Agent demos). Here is a brief overview of our XLang Agents framework. You can find more details about concepts & designs in our documentation.
Data Agent is equipped with data-related tools, allowing it to search, handle, manipulate, and visualize data efficiently. It is proficient in writing and executing code, enabling various data-related tasks.
Plugins Agent boasts integration with over 200 plugins from third-party sources. These plugins are carefully selected to cater to various aspects of your daily life scenarios. By leveraging these plugins, the agent can assist you with a wide range of tasks and activities.
Web Agent harnesses the power of a Chrome extension to navigate and explore websites automatically. This agent streamlines the web browsing experience, making it easier to find relevant information, access desired resources, and so on.
Please check here for full documentation, which will be updated to stay in pace with the demo changes and the code release.
Thanks to open-sourced communities’ efforts, such as LangChain, ChatBot UI, Taxy.ai browser extension and others. We are able to build our interface prototype much more conveniently and efficiently.
We welcome contributions and suggestions, together we move further to make it better!
- 🐛 Post an issue if you encounter any problems during your experience, or if you want to add any additional features.
- 🕹 Directly contribute to our repo by creating a Pull Request. Together we can make XLang better!
- ⭐ Give us a star, follow us on Twitter, share your own examples, and share with your friends!
Heartfelt appreciation to Ziyi Huang, Roxy Rong, Jansen Wong, and Chen Wu for their valuable contributions to the XLang Agents demo. Their expertise and insights were instrumental in bringing this project to fruition!