by stanfordnlp · AI 工具 · ★ 35.1k
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.
| Stars | 35,084 |
| Forks | 2,979 |
| Language | Python |
| Category | AI 工具 |
| License | MIT |
| Quality Score | 44.026/100 |
| Open Issues | 520 |
| Last Updated | 2026-06-16 |
| Created | 2023-01-09 |
| Platforms | python |
| Est. Tokens | ~14k |
These tools work well together with dspy for enhanced workflows:
Explore other popular ai 工具 tools:
dspy is DSPy: The framework for programming—not prompting—language models. It is categorized as a AI 工具 with 35.1k GitHub stars.
dspy is primarily written in Python.
You can find installation instructions and usage details in the dspy GitHub repository at github.com/stanfordnlp/dspy. The project has 35.1k stars and 2979 forks, indicating an active community.
dspy is released under the MIT license, making it free to use and modify according to the license terms.