The database of free AI tools on GitHub
23,066 open-source AI repos. Find a free alternative to any paid AI tool, or see what developers are talking about.
82 repos · showing 1–30
Build and deploy ML applications with a comprehensive Python framework.
Converts complex documents into LLM-ready formats for AI workflows.
Unified platform for fine-tuning 100+ large language models with CLI and Web UI.
Converts various document formats into structured data for AI processing.
Machine learning library for Python.
Transform physical documents into searchable digital archives.
Efficiently organizes and searches large-scale vector data for AI applications.
AI-powered photo and video organization and search.
Translate scientific PDF documents while preserving layout and formulas.
Advanced NLP library for Python with neural network models and pipelines.
Label data for machine learning models with a user-friendly UI.
Reproduce and extend the R1 pipeline for training and evaluating language models.
Generate and process audio with deep learning models.
Efficiently fine-tune large language models with parameter-efficient methods.
Compute embeddings and rerank texts using state-of-the-art models.
开源中文LLaMA和Alpaca大语言模型，支持本地训练和部署。
A fast, distributed gradient boosting framework for machine learning tasks.
Detects file types using a deep learning model.
Run Hugging Face's machine learning models in the browser.
Converts unstructured documents into structured data for LLMs.
A fast, open-source PDF parser for high-quality text extraction.
Train large language models from scratch using PyTorch.
A PyTorch toolkit for speech and text processing.
Multimodal vector search library for AI applications.
Detects and anonymizes sensitive data in text, images, and structured data.
Automates machine learning for tabular and time series data with minimal code.
Unified framework for time series analysis and machine learning tasks.
Extract text, metadata, images, and structured data from various document formats.
A fast, scalable library for gradient boosting on decision trees.
Joint embedding model for cross-modal learning across images, text, audio, depth, thermal, and IMU data.