Declarative framework from Stanford University for programming language models rather than prompting them. DSPy treats LLM interactions as programmable modules with input-output signatures and uses optimization algorithms to automatically compile these modules into effective prompts or fine-tuned weights, replacing brittle prompt strings with structured, modular AI software.
Open-source declarative framework from Stanford NLP for programming and automatically optimizing LLM pipelines (MIT). 100% free with $0 software cost; users only incur standard token costs from their underlying model providers during compilation and inference.
