Prompt Optimizer

Structured outputs for LLMs. Guarantees valid JSON, regex-compliant text, and Pydantic model outputs during generation. Trusted by NVIDIA, Cohere, Hugging Face, and vLLM. Apache 2.0 licensed.

Pioneering framework for structured and meta-prompt design. Battle-tested by thousands of users worldwide with 10,000+ stars. The most popular prompt engineering paradigm for creating reusable, maintainable prompt templates. Apache 2.0 licensed.

Efficient programming paradigm for steering language models. Control output structure with loops, conditionals, and regex constraints inline. Reduces latency and cost vs conventional prompting. MIT licensed.

Fast, flexible and portable structured generation engine. Default backend for vLLM, SGLang, TensorRT-LLM, and MLC-LLM with flexible grammar support and zero-overhead mask generation. Apache 2.0 licensed.

Library to build and auto-optimize LLM applications with LLM-AutoDiff for fine-tuning-free optimization. End-to-end workflow optimization with tracing and human-in-the-loop capabilities. MIT licensed.

Zero-dependency Python CLI that lints structured-output configs for vLLM, llama.cpp, and Ollama against 23 version-aware rules, catching silently-ignored fields before production. MIT licensed.