DSPy
Free tierThe framework for programming—not prompting—language models
Free·All audiences·Open source
Key strengths
Programming (not prompting) language modelsModular AI system composition in PythonAutomatic prompt and weight optimizationSupports classifiers, RAG pipelines, and agent loopsDeclarative Self-improving Python (DSPy) paradigm
Completely free
Founded 2022
Self-hostable
No ratings yet
DSPy is purpose-built for AI/ML researchers and developers working on:
- RAG pipelines — compose retrieval and generation modules with optimized prompts tuned end-to-end against a retrieval + answer quality metric.
- Agent loops — build multi-step reasoning agents using modules like
dspy.ReActwithout manually engineering each reasoning step's prompt. - Classifiers — define classification signatures and let DSPy optimizers find the best prompt or fine-tuned weights for the task.
- Modular AI systems — assemble complex, multi-module LM programs in Python that are easy to test, version, and improve automatically.
- Automatic prompt & weight optimization — replace manual prompt iteration with a metric-driven optimization loop over a development set.