Tool overview
DSPy is listed under AI Infrastructure & MLOps AI tools.
What is DSPy?
DSPy is an open-source Python framework for expressing language-model applications as modular programs and optimizing prompts or weights against measurable objectives. It supports retrieval, agents, evaluation, adapters, and many model providers.
Best for
Python teams building measurable and optimizable language-model programs
Who is it for?
Decision note
Rebuilt from the original export under the complete V412/V411 factual-source-verification workflow. Preview only. Apply remains blocked until Failures = 0, Warnings = 0, Unmapped = 0, Missing = 0; explicit clears are reviewed; image import is disabled or V380 accepts the asset; a representative WordPress edit screen is compared with the export and proposed row; and a post-Apply zero-change Preview succeeds.
Key features
Typed signatures and reusable modules
Prompt and weight optimizers
Evaluation, metrics, and tracing hooks
Model-provider and retrieval integrations
Use cases
Optimize RAG pipelines
Build modular agents
Tune classification and extraction programs
Evaluate LM system changes
Pros
- Free and MIT licensed
- Model-provider independent
- Separates program structure from prompt tuning
Cons
- Users still pay their model providers
- Optimization needs representative data
- Production deployment is the user’s responsibility
Limitations
DSPy does not host models or include their usage costs.
Optimization quality depends on metrics, examples, and evaluation design.
Pricing details
Billing options
Pricing note
DSPy is free and open source under the MIT license. Users pay separately for the models and infrastructure they connect.
Supported languages
- English
Integrations
OpenAI
Anthropic
Google Gemini
Databricks
Ollama
LiteLLM
Retrieval systems
Please log in to join the discussion.