#1414th of 20 in Agent frameworks and SDKs
dspy
Python framework for programming LMs and optimizing their prompts and weights
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 38.6k
- License
- MIT
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- Python
32,909 on 25 Mar 202638,639 on 14 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
DSPy lets you describe LM-based systems as modular Python code instead of hand-written prompts. It includes optimizers that tune prompts and model weights against a metric, and targets classifiers, RAG pipelines and agent loops. It installs with pip; the README defers all usage details to dspy.ai.
Who it is for: Python developers building and tuning LM pipelines, RAG and agents
Strengths
- Optimizers tune prompts and weights against a metric, including GEPA
- Programs are composed as Python modules rather than prompt strings
- Backed by published Stanford NLP research papers
- Single pip install; MIT license
Weaknesses
- README has no quickstart or code example; usage lives on the external docs site
- Optimization needs a metric and example data, adding setup versus plain prompting
- Supported model providers are not listed in the README
- Library only: no UI, server or deployment tooling
Also in Agent frameworks and SDKs
See all 20| Rank | Project | Score |
|---|---|---|
| 1 | ppt-masterAgent skill that turns documents into natively editable PowerPoint decks | 90 out of 100 |
| 2 | langchainPython framework for building LLM agents and apps from interoperable components | 88 out of 100 |
| 3 | browser-usePython library that lets an LLM agent control a web browser | 88 out of 100 |
| #4 | tradingagentsLangGraph multi-agent framework simulating a trading firm to analyze tickers | 86 out of 100 |
| #5 | crewaiPython framework for multi-agent workflows with role-based Crews and event-driven Flows | 80 out of 100 |