Run quantum chemistry workflows, visualize molecules, and extract chemical insights—just by chatting. El Agente makes it easy to explore computational chemistry or deploy workflows to solve chemical problems, whether you’re a student, an academic or industrial researcher.
El agente is an AI for science system developed by the Matter Lab at the University of Toronto, The Acceleration Consortium, and NVIDIA.
For advanced features like full workflow exports, interactive visualizations, and detailed case studies, check out the full El Agente platform.
A multi-agent system
El Agente is a multi-agent system designed to democratize quantum chemistry workflows through natural language interaction.
Powered by a complex system that harnesses large language models (LLMs), El Agente streamlines the generation, execution, and interpretation of computational chemistry tasks. It enables users to design workflows, run simulations, and extract chemical insights using plain English—making advanced quantum chemistry more accessible than ever.
El Agente supports a wide range of tasks, from geometry optimizations to property predictions, across various levels of theory and computational backends. Users can interact with the system through a chat embedded in our graphical user interface (GUI), visualize molecular structures, and export action traces to reproduce workflows.
The platform is designed with transparency and usability in mind. Intermediate results can be inspected and reused, and the multi-agent design ensures efficient task management, even in complex scenarios.
If you are interested in working with El Agente, click here for pre-registration, and receive our tutorials for examples of how El Agente can be used in teaching and research settings.
Several sample workflows and datasets from our case studies and course modules are available for download in the paper. These examples demonstrate El Agente’s potential in real-world research and educational environments.
El Agente: An Autonomous Agent for Quantum Chemistry
Computational chemistry tools are widely used to study the behaviour of chemical phenomena. Yet, the complexity of these tools can make them inaccessible to non-specialists and challenging even for experts. In this work, we introduce El Agente Q, an LLM-based multi-agent system that dynamically generates and executes quantum chemistry workflows from natural language user prompts. The system is built on a novel cognitive architecture featuring a hierarchical memory framework that enables flexible task decomposition, adaptive tool selection, post-analysis, and autonomous file handling and submission. El Agente Q is benchmarked on six university-level course exercises and two case studies, demonstrating robust problem-solving performance (averaging > 87% task success) and adaptive error handling through in-situ debugging. It also supports longer-term, multi-step task execution for more complex workflows, while maintaining transparency through detailed action trace logs. Together, these capabilities lay the foundation for increasingly autonomous and accessible quantum chemistry.
Alpha Sign-up
Sign up to be notified of the alpha version of El Agente Cloud.
