Claude Code for DSPy
Comprehensive CLI to Build and Optimize Your DSPy Code
Develop DSPy Applications • Optimize with GEPA
💡 Note
DSPy Code is in its initial release and under active development. The quality and effectiveness of generated code depends on several factors: the language model you connect, MCP (Model Context Protocol) servers you integrate, and the context you provide to DSPy Code. We're continuously improving based on community feedback.
See It In Action
Watch DSPy Code generate production-ready code in real-time
What is DSPy Code?
Your AI-Powered DSPy Development Assistant
Starting a New DSPy Project
Perfect for building a new AI application from scratch, prototyping ideas quickly, and learning DSPy fundamentals.
- Complete project structure
- Configuration files
- Example programs
- Best practices setup
- Ready to code in 2 minutes
Example: I want to build a customer support chatbot with sentiment analysis and automated responses.
Optimizing DSPy Programs with GEPA
Perfect for improving accuracy of existing programs, automatic prompt engineering, and production optimization.
- Real GEPA execution
- Automated metric functions
- Progress tracking & resumption
- Production-ready optimized code
- Performance improvements documented
Example: My sentiment analyzer needs optimization. Optimize it with GEPA to improve accuracy.
Adding DSPy to Existing Projects
Perfect for enhancing existing Python applications, adding AI capabilities to current systems, and modernizing legacy code.
- Minimal setup (no disruption)
- Scans your existing code
- Understands your project structure
- Generates code that fits your style
- Works alongside your current code
Example: I have a Django app. I want to add AI-powered document summarization.
Learning DSPy (No Docs Required!)
Perfect for first time using DSPy, understanding DSPy concepts, and exploring different patterns.
- No reading required
- Learn by building
- Ask questions in natural language
- Answers using YOUR installed DSPy version
Example: What is a DSPy Signature? How does ChainOfThought work?
Connecting to MCP Servers
DSPy Code is an MCP Client! Connect to any MCP server to supercharge your DSPy programs with external tools, APIs, and data sources.
- Access external tools
- Read from data sources
- Execute commands
- Integrate services
- Build powerful workflows
Example: Build a RAG system that uses MCP to query my company's database and generate answers.
Building Production AI Applications
Perfect for enterprise applications, production deployments, and mission-critical systems.
- Validated, production-ready code
- Best practices built-in
- Error handling and logging
- Type hints and documentation
- Optimized performance
- Export as packages
Quality score: 90+ out of 100 automatically!
The Complete Workflow
From idea to production-ready DSPy application in one platform
Phase 1: Development
Build your DSPy application from scratch or enhance existing code.
/init - Initialize project/validate - Ensure best practicesPhase 2: Optimization
Optimize your working code with GEPA for production.
/data - Generate training examples/optimize - Run GEPA optimization/eval - Evaluate improvements/export - Package for deployment🎯 The Result
Production-ready DSPy applications with optimized performance, evolved prompts, and documented improvements
Who is This For?
DSPy Code is designed for everyone, from beginners to production teams
Complete Beginners
Never used DSPy before? Perfect! Start here and learn by doing. The CLI teaches you DSPy concepts as you build real programs.
No prerequisites needed.
DSPy Developers
Already know DSPy? Supercharge your workflow with AI-powered code generation, validation, and optimization.
Build faster, optimize smarter.
Production Teams
Building production DSPy applications? Get validated, optimized, production-ready code with GEPA optimization and best practices built-in.
Ship with confidence.
✨ Key Features
Everything you need to build and optimize DSPy applications
Natural Language Interface
Describe what you want in plain English. The CLI generates complete, working DSPy code.
"Build a RAG system for document Q&A"
Real GEPA Optimization
Not mocked. Real GEPA (Genetic Pareto) optimization that improves your programs by 10-30% automatically.
Real GEPA optimization that improves accuracy automatically!
Smart Validation
Every generated code is validated for quality, best practices, and correctness. Score: 90+/100.
Ship with confidence
Version-Aware Intelligence
Adapts to YOUR installed DSPy version. Answers questions using your actual code, not outdated docs.
Always current. Always accurate.
Built-in MCP Client
Connect to any MCP server to access external tools, APIs, databases, and services in your DSPy programs.
Build powerful, connected AI applications.
Learn as You Build
No docs, books, or tutorials needed. Ask questions, get answers from your code, build in real-time.
Interactive learning experience.
Codebase Knowledge
Indexes your DSPy installation and project. Ask questions about your own code!
"Explain my RAG module" - Done!
Universal Model Support
Connect to any LLM: Ollama (local), OpenAI, Anthropic, Gemini. Switch anytime.
Your choice, your control.
Visual Workflow
See how DSPy Code transforms your development process
Type Command
Natural language
AI Generates
Complete code
Validated
Best practices
Deploy
Production ready
💬 Real Workflows
See how different users leverage DSPy Code
Workflow 1: Complete Beginner
- →Install DSPy Code
- →/init --fresh
- →"What is DSPy?"
- →"Create a simple text classifier"
- →/save my_first_program.py
- →/run
Result: Working DSPy program, understanding of basics
Workflow 2: Building Production App
- →dspy-code /init in existing project
- →Generate signatures, modules, programs
- →Generate 200 training examples
- →Optimize with GEPA
- →Validate code quality
- →Export as package
- →Deploy
Result: Production-ready AI application
Workflow 3: Learning Advanced Patterns
- →"Show me how ReAct works"
- →"Create a multi-agent system"
- →"Explain GEPA optimization"
- →"Build a RAG system with custom retrieval"
Result: Deep understanding through hands-on building
Quick Start
Get started in minutes
Install
pip install dspy-codeStart
dspy-codeBuild
/init
/connect ollama
Create a [your app]Why DSPy Code?
The only CLI that combines AI-powered code generation with real GEPA optimization
AI-Powered
Natural language to production code. No manual coding required.
Real GEPA
Actual Genetic Pareto optimization, not mocked. Real performance improvements.
Validated Code
Every generated code is validated for quality, best practices, and correctness.
Version-Aware
Adapts to YOUR installed DSPy version. Always current, always accurate.
Common Questions
Do I need to know DSPy first?
No! That's the whole point. DSPy Code teaches you as you build. Just start creating and ask questions when you need help.
Can I use this with my existing DSPy code?
Yes! Run /init in your project directory. DSPy Code will scan your code and help you extend it.
What models can I use?
Any! Ollama (local), OpenAI, Anthropic, Gemini. Connect with one command: /connect ollama llama3.1:8b
Is the optimization real or mocked?
Real GEPA optimization! Actual Genetic Pareto optimization that improves accuracy by 10-30%.
Do I need to read documentation?
No! Just ask DSPy Code. It answers questions using your actual installed DSPy version.
Start Building in 2 Minutes
No docs to read. No tutorials to follow. Just start building.
pip install --upgrade dspy-code