Show HN: LLML: Data Structures => Prompts I've been building AI systems for a while and kept hitting the same wall - prompt engineering felt like string concatenation hell. Every complex prompt became a maintenance nightmare of f-strings and template literals. So I built LLML - think of it as React for prompts. Just as React is data => UI, LLML is data => prompt. The Problem:
Why XML-like? We found LLMs parse structured formats with clear boundaries (<tag>content</tag>) more reliably than JSON or YAML. The numbered lists (<rules-1>, <rules-2>) prevent ordering confusion.Available in Python and TypeScript:
Experimental Rust and Go implementations also available for the adventurous :)Key features:
The formatter system is particularly neat - you can override how any data type is serialized, making it easy to handle domain-specific objects or sensitive data.GitHub: https://github.com/zenbase-ai/llml Would love to hear if others have faced similar prompt engineering challenges and how you've solved them! |
No comments yet