Home Projects promptsource
promptsource
Python

promptsource

Toolkit for creating, sharing and using natural language prompts.

by bigscience-workshop · GitHub
Stars
Forks
License
Created
Last commit
Language
machine-learningnatural-language-processingnlpApache-2.0Python
View on GitHub
In plain words

Create and share prompts to help AI understand and perform various tasks better.

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
promptsource — GitHub preview card
📈 Star history
3 0273 026
2026-07-072026-08-31
📈 Track promptsource

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

Toolkit for creating, sharing and using natural language prompts.

promptsource has 3k stars on GitHub. It has been forked 377 times. promptsource is written mainly in Python. It has been in active development since 2021. promptsource is available under the Apache-2.0 license. Its main topics are machine-learning, natural-language-processing, nlp.

Frequently asked questions

What is promptsource?

Toolkit for creating, sharing and using natural language prompts.

Is promptsource open source?

promptsource is an open-source project. It is released under the Apache-2.0 license.

Is promptsource free?

Yes. promptsource is free and open source — you can use, modify and self-host it.

What license does promptsource use?

promptsource is available under the Apache-2.0 license.

What language is promptsource written in?

promptsource is written mainly in Python.

🏅 Maintainer of this project?
olud.ai badge — promptsource

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=bigscience-workshop-promptsource)](https://olud.ai/project/bigscience-workshop-promptsource.html)
More badge options →
🧬 Shares DNA with

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.