Transformers
State-of-the-art Machine Learning library for Pytorch, TensorFlow, and JAX, providing thousands of pre-trained models for natural language processing, computer vision, and other areas.
There are 3 open-source alternatives to spaCy in this directory. The most popular is Transformers with 159.2k GitHub stars, followed by Haystack(24.8k stars). All are open source, free to use, and many can be self-hosted.
| # | Tool | Stars | Language | License |
|---|---|---|---|---|
| 1 | Transformers State-of-the-art Machine Learning library for Pytorch, TensorFlow, and JAX, providing thousands of pre-trained models for natural language processing, computer vision, and other areas. | 159.2k | Python | Apache License 2.0 |
| 2 | Haystack AI orchestration framework to build customizable, production-ready LLM applications. Connect components such as models, vector databases, and file converters to pipelines or agents that can interact with your data. Best suited for building Retrieval-Augmented Generation (RAG), question answering, semantic search, or conversational agent chatbots. | 24.8k | MDX | Apache License 2.0 |
| 3 | Chonkie 🦛 CHONK your texts with Chonkie ✨ — The no-nonsense RAG chunking library. A powerful and efficient tool for text chunking and processing. | 3.9k | Python | MIT License |
State-of-the-art Machine Learning library for Pytorch, TensorFlow, and JAX, providing thousands of pre-trained models for natural language processing, computer vision, and other areas.
AI orchestration framework to build customizable, production-ready LLM applications. Connect components such as models, vector databases, and file converters to pipelines or agents that can interact with your data. Best suited for building Retrieval-Augmented Generation (RAG), question answering, semantic search, or conversational agent chatbots.
🦛 CHONK your texts with Chonkie ✨ — The no-nonsense RAG chunking library. A powerful and efficient tool for text chunking and processing.
The top three are Transformers(159.2k stars), Haystack(24.8k stars), Chonkie(3.9k stars). All are open source and free to use.
Yes. Every tool listed here is open source and free to use in your own projects. Many can be self-hosted on your own infrastructure, which means no subscription fees and full control over your data.
Many of the alternatives listed are self-hostable. Each tool's page lists hosting details, system requirements, and licensing terms.
Get notified about new tools and updates to existing ones.