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:

# We've all written this... prompt = f"Role: {role}\n" prompt += f"Context: {json.dumps(context)}\n" for i, rule in enumerate(rules): prompt += f"{i+1}. {rule}\n" # The Solution: from zenbase_llml import llml # Compose prompts by composing data context = get_user_context() prompt = llml({ "role": "Senior Engineer", "context": context, "rules": ["Never skip tests", "Always review deps"], "task": "Deploy the service safely" }) # Output: <role>Senior Engineer</role> <context> ... </context> <rules> <rules-1>Never skip tests</rules-1> <rules-2>Always review deps</rules-2> </rules> <task>Deploy the service safely</task>

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:

pip/poetry/uv/rye install zenbase-llml npm/pnpm/yarn/bun install @zenbase/llml

Experimental Rust and Go implementations also available for the adventurous :)

Key features:

- ≤1 dependencies - Extensible formatter system (create custom formatters for your domain objects) - 100% test coverage (TypeScript), 92% (Python) - Identical output across all language implementations

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!