SoftwareFramework

DSPy

Version 3.4.0

DSPy is an open-source Python framework for building language-model programs from compositional Python modules instead of hand-written prompts. It includes optimizer algorithms that tune the prompts and weights of those programs. The project started at the Stanford NLP group.1 3

Repository: GitHub repository (external site: github.com)
Documentation: Documentation (external site: dspy.ai)
Release notes: Release 3.4.0 (external site: github.com)
License: License (MIT) (external site: raw.githubusercontent.com)

Last reviewedSep 29, 2026Entry updated Sep 29, 2026Documented release Sep 25, 2026

Availability and license

Overall availability

Public

Source code on GitHub under the MIT License; installable from PyPI as dspy.1 2 4

Availability is separate from permission: read the license before using or redistributing.

MIT License (external site: raw.githubusercontent.com)2
Applies to: Code · SPDX MIT · on the rubric’s OSI-approved list

Public materials checklist

Items for a framework under USASI rubric v0.1. Unknown means unassessed or insufficient evidence.

Public materials checklist for DSPy
Item	Status	Notes and evidence
Source codeIs the source code publicly readable?	Public	Published on GitHub under the MIT License.1 2
DocumentationIs user documentation published?	Public	Documentation is published at dspy.ai.1 3
InstallationAre installation instructions or packages publicly available?	Public	Installed with pip from PyPI, or directly from the main branch on GitHub for the latest changes.1 3
Supported platformsAre supported operating systems or hardware documented?	Partial	PyPI metadata requires Python 3.10 or later and earlier than 3.15. The pages read do not give an operating-system or hardware support matrix.4
Release statusAre versioned releases published?	Public	Versioned releases are published on GitHub and PyPI; 3.4.0 was released on 2026-09-25.5 4

What it is useful for

Building modular language-model systems, such as classifiers, retrieval-augmented generation pipelines, and agent loops, and optimizing their prompts and weights.1

Organization context

Stanford University

U.S. eligibility

Project eligibility rests on documented governing or maintaining entities, not on contributors.

Eligible · basis: U.S.-governed project

The DSPy repository sits in the Stanford NLP GitHub organization, which gives its location as Stanford, California. The Stanford NLP Group's website lists DSPy among the software it develops. The MIT license names Stanford Future Data Systems as the copyright holder, and the documentation says the project started at Stanford NLP. Contributors come from many organizations; eligibility rests on the Stanford hosting documented above.6 7 2 3

Assessed Sep 29, 2026

Sources

1.
DSPy README (external site: raw.githubusercontent.com)
Stanford NLP Group · Repository · accessed Sep 29, 2026
2.
DSPy LICENSE (external site: raw.githubusercontent.com)
Stanford NLP Group · License · accessed Sep 29, 2026
3.
Overview - DSPy (external site: dspy.ai)
DSPy project · Documentation · accessed Sep 29, 2026
4.
dspy on PyPI (external site: pypi.org)
Python Package Index · Documentation · published Sep 25, 2026 · accessed Sep 29, 2026
5.
Release 3.4.0 · stanfordnlp/dspy (external site: github.com)
Stanford NLP Group · Release notes · published Sep 25, 2026 · accessed Sep 29, 2026
6.
Stanford NLP on GitHub (external site: github.com)
Stanford NLP Group · Repository · accessed Sep 29, 2026
7.
The Stanford Natural Language Processing Group (external site: nlp.stanford.edu)
Stanford NLP Group · Official page · accessed Sep 29, 2026

Report a correction Edit this entry

This listing is not an endorsement, a safety assessment, or a federal approval.