Guidance
Guidance language for controlling LLM generation with constraints, grammars, and JSON schemas.
About
Guidance is a language for programmatically controlling large language models through constrained generation. It supports regex patterns, context-free grammars, and JSON schemas, and integrates with Transformers, llama.cpp, and OpenAI-compatible APIs. The framework saves tokens through fast-forwarding by pre-filling tokens implied by the grammar instead of always sampling.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Category
- AI Frameworks & Libraries
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Intermediate (3/5)
- License
- MIT
- Added
- May 7, 2026
Related Tools
JAX neural network library with PyTorch-like module system.
High-level deep learning API supporting JAX, TensorFlow, and PyTorch backends.
Neural network library for JAX by Google providing Linen module system.
Deep learning platform by Baidu with industrial-strength deployment tools.
Hugging Face library for state-of-the-art NLP models
End-to-end open-source ML platform by Google for training and deployment.
Mentioned in
SGLang and the Structured-Output Renaissance
Constrained generation used to be a library you bolted on. It is becoming a feature of the inference engine....
Max P
DSPy and the Rise of Programmatic Prompting
DSPy reframes prompts as code that can be compiled and optimized. Here is what that actually means, why it...
Max P