Guidance

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.

AI prompt optimization tool with multi-round iterative improvements, dual-mode optimization for system and user prompts, and multi-model support. Available as web app, desktop app, Chrome extension, and Docker deployment. AGPL-3.0 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.