DSPy — Agents-OSS

Overview

You declare what each step should do and supply a metric; the optimiser searches for the prompts and few-shot examples that maximise it. The payoff is that improving a pipeline becomes measurable rather than superstitious. It requires an evaluation set — without one there is nothing to optimise against.

What can you do with DSPy?

Compose modules instead of prompts — pip install dspy gives you Python modules you compose into classifiers, RAG pipelines or agent loops, leaving the prompt text as something the framework produces rather than something you hand-write.
Optimize weights, not only prompts — The framework includes algorithms for tuning model weights alongside prompts, with the Jul'24 paper covering how fine-tuning and prompt optimization work together.
Read the method before adopting — The README indexes the underlying research: GEPA (Jul'25) arguing that reflective prompt evolution can outperform reinforcement learning, the Jun'24 paper on optimizing instructions and demonstrations for multi-stage programs, and the Oct'23 paper on compiling declarative LM calls into self-improving pipelines.

Documentation

Reproduced from the stanfordnlp/dspy README, published under MIT. Read the original ↗

DSPy: Programming—not prompting—Foundation Models

Documentation: DSPy Docs

DSPy is the framework for programming—rather than prompting—language models. It allows you to iterate fast on building modular AI systems and offers algorithms for optimizing their prompts and weights, whether you’re building simple classifiers, sophisticated RAG pipelines, or Agent loops.

DSPy stands for Declarative Self-improving Python. Instead of brittle prompts, you write compositional Python code and use DSPy to teach your LM to deliver high-quality outputs. Learn more via our official documentation site or meet the community, seek help, or start contributing via this GitHub repo and our Discord server.

Documentation: dspy.ai

Please go to the DSPy Docs at dspy.ai

Installation

pip install dspy

To install the very latest from main:

pip install git+https://github.com/stanfordnlp/dspy.git

📜 Citation & Reading More

If you’re looking to understand the framework, please go to the DSPy Docs at dspy.ai.

If you’re looking to understand the underlying research, this is a set of our papers:

[Jul’25] GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
[Jun’24] Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programs
[Oct’23] DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines
[Jul’24] Fine-Tuning and Prompt Optimization: Two Great Steps that Work Better Together
[Jun’24] Prompts as Auto-Optimized Training Hyperparameters
[Feb’24] Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models
[Jan’24] In-Context Learning for Extreme Multi-Label Classification
[Dec’23] DSPy Assertions: Computational Constraints for Self-Refining Language Model Pipelines
[Dec’22] Demonstrate-Search-Predict: Composing Retrieval & Language Models for Knowledge-Intensive NLP

To stay up to date or learn more, follow @DSPyOSS on Twitter or the DSPy page on LinkedIn.

The DSPy logo is designed by Chuyi Zhang.

If you use DSPy or DSP in a research paper, please cite our work as follows:

@inproceedings{khattab2024dspy,
  title={DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines},
  author={Khattab, Omar and Singhvi, Arnav and Maheshwari, Paridhi and Zhang, Zhiyuan and Santhanam, Keshav and Vardhamanan, Sri and Haq, Saiful and Sharma, Ashutosh and Joshi, Thomas T. and Moazam, Hanna and Miller, Heather and Zaharia, Matei and Potts, Christopher},
  journal={The Twelfth International Conference on Learning Representations},
  year={2024}
}
@article{khattab2022demonstrate,
  title={Demonstrate-Search-Predict: Composing Retrieval and Language Models for Knowledge-Intensive {NLP}},
  author={Khattab, Omar and Santhanam, Keshav and Li, Xiang Lisa and Hall, David and Liang, Percy and Potts, Christopher and Zaharia, Matei},
  journal={arXiv preprint arXiv:2212.14024},
  year={2022}
}