DSPy

Spec sheet

What it does

DSPy is a Python framework for building AI systems by expressing tasks as structured signatures instead of prompts.Read 9 Oct 2026 · dspy.ai

Deployment

The documentation describes deploying DSPy programs with FastAPI or MLflow.Read 9 Oct 2026 · dspy.ai

Integrations

DSPy uses LiteLLM to normalize inference providers and says it can connect to nearly any model and provider supported by LiteLLM.Read 8 Oct 2026 · dspy.ai

Support

The site links to a DSPy Discord community and GitHub repository.Read 8 Oct 2026 · dspy.ai

License

The project is listed as MIT licensed.Read 9 Oct 2026 · dspy.ai

Founded

2022Read 28 Sep 2026 · dspy.ai

Agent tools

DSPy supports tool-using agents through `dspy.ReAct` and manual tool handling with `dspy.Tool` and `dspy.ToolCalls`.Read 8 Oct 2026 · dspy.ai

API serving

The deployment guide shows serving a DSPy program as a REST API with FastAPI.Read 9 Oct 2026 · dspy.ai

Community integrations

The community page lists integrations and providers including Weaviate, Qdrant, LangChain, Langfuse, and Weights & Biases Weave.Read 8 Oct 2026 · dspy.ai

Community project limits

The site says community-maintained language ports are not officially supported by the DSPy team and their feature availability and API compatibility may vary.Read 8 Oct 2026 · dspy.ai

Community support

The overview links to DSPy documentation, GitHub, and Discord community resources.Read 9 Oct 2026 · dspy.ai

Install

DSPy can be installed with `pip install dspy` or `uv add dspy` and works in Python 3.10+ environments.Read 8 Oct 2026 · dspy.ai

Installation

DSPy can be installed with pip or uv and works in Python 3.10+ environments.Read 9 Oct 2026 · dspy.ai

Model integrations

DSPy uses LiteLLM to normalize inference providers and accepts LiteLLM model strings, including options from Anthropic, Google, and OpenRouter.Read 9 Oct 2026 · dspy.ai

Modules

DSPy modules provide different execution strategies, including reasoning, ensembles, tools, and REPL use.Read 9 Oct 2026 · dspy.ai

Multimodal

The overview describes images as a Signature field type for multimodal tasks.Read 8 Oct 2026 · dspy.ai

Optimization

DSPy optimizers compile programs against a metric using examples and a scoring function.Read 9 Oct 2026 · dspy.ai

Origin

DSPy says it started at Stanford NLP and was built in the open beginning in December 2022.Read 8 Oct 2026 · dspy.ai

Project origin

DSPy says it started at Stanford NLP and describes itself as built in the open since December 2022.Read 9 Oct 2026 · dspy.ai

Provider examples

The setup guide names OpenAI, Anthropic, Google, and OpenRouter as provider options.Read 8 Oct 2026 · dspy.ai

Signatures

Signatures define tasks as typed inputs and outputs.Read 9 Oct 2026 · dspy.ai

Tool integrations

DSPy can bridge remote MCP tools into its tool interface.Read 9 Oct 2026 · dspy.ai

Who it is for

The overview presents DSPy for building AI programs and systems, including agent, extraction, and multimodal tasks.Read 9 Oct 2026 · dspy.ai

Where Specifiction places it

• LLM Application Development Frameworks#10 of 497.6
• Llm Developer Tools#15 of 267.5
• AI Prompt Generators#17 of 287.7
• AI Orchestration Software#14 of 207.5
• Prompt Engineering Tools#20 of 257.5