Promptify is an open-source, task-based NLP library that turns large language models into structured, production-friendly pipelines. Its creators describe it as a kind of scikit-learn for LLM-powered NLP: instead of hand-writing prompts for every task, you call typed task functions and get validated, structured results back.
Promptify covers the classic NLP workload โ named entity recognition, text classification, question answering, summarization, relation extraction, table extraction, SQL generation and topic modeling โ but executes it through LLMs with Pydantic-validated outputs, so downstream code receives objects rather than raw text. A universal backend layer built on LiteLLM lets the same task code run against more than a hundred model providers, making it easy to switch between hosted APIs and local models. Batch processing and asynchronous execution support larger workloads, and built-in evaluation and cost tracking help teams understand quality and spend per task. The library installs from PyPI with a single pip command. An active community shares prompts, task configurations and research notes, and the project positions itself as shared infrastructure for prompt-engineering practice rather than a single-model wrapper. Promptify is Apache-2.0 licensed, has more than 4,600 stars on GitHub, and was still receiving updates in 2026.
Free. Promptify is open source under the Apache-2.0 license; you only pay for any hosted model APIs you choose to call through it.
Python developers and data teams who need classic NLP tasks done by LLMs with predictable, typed results, and who want one consistent API across many model providers rather than provider-specific prompt code.