Skip to content
Agentmart
Submit a tool

DSPy

Python framework for writing language-model programs as code and optimizing their prompts and weights instead of hand-tuning prompts.

Harness by Stanford NLP

IndexedMIT★ 38,766
Write a review

Install

From the package registry. Read the repository before you give any tool access to your data.

pip install dspy

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

DSPy lets developers build modular AI systems by writing compositional Python code rather than prompt strings. It includes algorithms that optimize the prompts and weights of those systems, and the README names classifiers, RAG pipelines and agent loops as use cases. The name stands for Declarative Self-improving Python, and the project is tied to a series of Stanford NLP research papers.

Use cases: prompt-engineering, knowledge-base

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Fact sheet

Languages
PythonREADME
Packages
dspy (pypi)README
Maturity
Stablegithub.com

Facts extracted by Claude Sonnet 5.5 from the linked sources on Oct 24, 2026; reviewed Oct 24, 2026. Wrong fact? Tell us.

Alternatives

Frameworks for the same language with a similar way of orchestrating agents.

Compare and alternatives

Featured in

Signals

Stars
38,766
Forks
3,452
Open issues
367
Weekly downloads
1,254,893
Last commit
Oct 22, 2026 (4 days ago)
Last release
Oct 12, 2026 (14 days ago)
Last package publish
Oct 12, 2026 (14 days ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Packages
pypi dspy
License
MIT
Website
dspy.ai/
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Cite this page

DSPy. Agent Mart. https://agentmart.dev/harnesses/dspy (last updated 2026-10-24)