# DSPy — card for AI agents

Framework for optimizing LLM prompts and pipelines systematically.

Category: Prompts, structured output and evals · PyPI package `dspy` · latest version 3.4.1 (checked 2026-11-01)
Install: `pip install dspy`
License: MIT (permissive)

In your own product (generator, app, hosted service): **yes**. Permissive license: ship it inside your own product, closed or open source, and keep its license and copyright notice.

## Agent Skills for it
- dspy from Orchestra-Research/AI-Research-SKILLs: `npx skills add Orchestra-Research/AI-Research-SKILLs --skill dspy`
- dspy from mateaix/mateclaw: `npx skills add mateaix/mateclaw --skill dspy`

## Numbers (AgentGid data)
- Gid Score: 62.7 (#754 of all tools, 4 of 78 in its category)
- Used in 6 public projects set up for AI coding agents (0.1%)
- Downloads last week: 1,467,956 (as of 2026-11-17), +0.9% over 4 weeks
- GitHub stars: 39,103 (as of 2026-11-17)
- Last push: 2026-11-13

## Often used with
NumPy 63.0%, python-dotenv 60.5%, pandas 59.7%, OpenAI Python Library 56.3%, Pydantic 55.5%, Requests 47.9%

## Checked alternatives (same job)
- Ragas: https://agentgid.com/tools/ragas/agent.md

## Links
- AgentGid page: https://agentgid.com/tools/dspy/
- Homepage: https://github.com/stanfordnlp/dspy
- Repository: https://github.com/stanfordnlp/dspy

---
AgentGid's catalog is curated: every entry was checked against the maker's official pages (registry, repository, license and pricing pages) on the date shown; a license value shows the quote it stands on wherever AgentGid has one. Usage numbers come from AgentGid's own scan of public repositories set up for AI coding agents. Claims by makers are reported, not tested by AgentGid.
