Promptify and promptml

These are complementary tools: Promptify provides a framework for prompt engineering and versioning with structured output handling, while PromptML offers a markup language specification that could be used as an input format or templating syntax within such a framework.

Promptify
74
Verified
promptml
52
Established
Maintenance 16/25
Adoption 14/25
Maturity 25/25
Community 19/25
Maintenance 6/25
Adoption 9/25
Maturity 25/25
Community 12/25
Stars: 4,572
Forks: 361
Downloads: 62
Commits (30d): 2
Language: Python
License: Apache-2.0
Stars: 60
Forks: 7
Downloads:
Commits (30d): 0
Language: Python
License: MIT
No Dependents
No risk flags

About Promptify

promptslab/Promptify

Prompt Engineering | Prompt Versioning | Use GPT or other prompt based models to get structured output. Join our discord for Prompt-Engineering, LLMs and other latest research

Provides task-specific NLP classes (NER, classification, QA, relation extraction) that return type-safe Pydantic models instead of raw text, eliminating parsing brittleness. Abstracts away LLM provider differences through LiteLLM, allowing seamless switching between OpenAI, Anthropic, Ollama, and 100+ other backends with a single model string. Includes built-in evaluation metrics (precision, recall, F1) and cost tracking, plus batch/async processing for production workloads.

About promptml

narenaryan/promptml

Prompt markup language (A.K.A PromptML) library is specially built for AI systems - from Vidura AI

Provides a structured DSL that decomposes prompts into explicit sections—context, objective, instructions, examples, constraints, and metadata—parsed into standardized data structures. Supports variable interpolation and serialization to XML, YAML, and JSON formats, enabling version control and cross-agent prompt reusability. Integrates with OpenAI and Google models via the companion `promptml-cli` tool.

Scores updated daily from GitHub, PyPI, and npm data. How scores work