This is an LLM agent framework and symbolic learning system designed for building self-evolving autonomous agents. It functions as a computational graph orchestrator that organizes agent interactions and tool sequences as a trainable graph of nodes. The framework focuses on data-centric agent optimization, allowing agent pipelines and prompts to be upgraded through data-driven training rather than manual engineering. It utilizes a symbolic learning process that applies language-based loss and textual reflections to refine the operational logic and symbolic components of an agent. The system
WrenAI is a platform designed to enable natural language interaction with relational and analytical databases. By combining a text-to-SQL engine with semantic data modeling, it allows users to explore structured data through plain language questions, removing the requirement for manual code generation. The system functions by grounding natural language requests in a predefined business logic layer rather than raw database schemas. This semantic approach, supported by context-aware prompt engineering, ensures that generated queries remain consistent and accurate across an organization. The pla
Official implementation for "Multimodal Chain-of-Thought Reasoning in Language Models" (stay tuned and more will be updated)