Pipelines & RAGOpen Source✦ Free Tier

DSPy

Programming (not prompting) LLMs

⭐ 18,000 stars● Health 80 — ActiveApp Infrastructure
Open in Builder →Website ↗GitHub ↗

About

Stanford's framework for algorithmically optimizing LLM pipelines. Replaces hand-crafted prompts with declarative modules and automatic optimization.

Choose DSPy when…

  • •You want to optimize LLM pipelines programmatically
  • •You're running experiments and tuning prompts at scale
  • •Academic or research-oriented LLM workflows fit you

Builder Slot

How do your AI calls chain together?Optional for most stacks

The pipeline layer that connects LLM calls, retrieval, and data processing into a workflow

Dev Tools
Not applicable
App Infra
Optional
Hybrid
Optional

Other tools in this slot:

LangChainLlamaIndexFlowiseDifyn8nHaystackLangflowVercel AI SDK+3 more

Stack Genome Detection

AIchitect's Genome scanner detects DSPy in your project via these signals:

pip packages
dspy-aidspy

Integrates with (1)

LiteLLMLLM Infrastructure

DSPy routes its compilation and inference calls through LiteLLM, enabling multi-provider optimization runs.

→ Model-agnostic DSPy compilation — optimize prompts across Claude, GPT-4o, and open models in one run to find the best-performing variant.

Compare →

Often paired with (1)

LangChain

Pricing

✦ Free tier available

Badge

Add to your GitHub README

DSPy on AIchitect[![DSPy](https://aichitect.dev/badge/tool/dspy)](https://aichitect.dev/tool/dspy)

Explore the full AI landscape

See how DSPy fits into the bigger picture — browse all 207 tools and their relationships.

Explore graph →