XGrammar

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.

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.

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.