Data, ML & Research covers 87 AI tools, with the top 10 averaging 106,258 community votes. 74 of the tools here are open source or have significant community traction. This page ranks them by all-time community votes, not by paid placement.
The current top three: tensorflow, ollama, transformers. Each entry below shows the tool, its open-source stars or community size, and a short description from the project's own README. Click through to a full review for pricing, alternatives, and what it's actually good at.
Looking for something specific? Try the AI tool search engine โ it indexes every tool on saas.pet and will surface what fits your workflow, not just what has the most votes.
An Open Source Machine Learning Framework for Everyone
Get up and running with Kimi-K2.6, GLM-5.1, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
๐ค Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
LLM inference in C/C++
Tensors and Dynamic neural networks in Python with strong GPU acceleration
scikit-learn: machine learning in Python
Deep Learning for humans
A lightweight coding agent for open models like Deepseek, Kimi, and Qwen
Inference code for Llama models
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
๐ธ๐ฌ - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
TensorFlow code and pre-trained models for BERT
Opiniated RAG for integrating GenAI in your apps ๐ง Focus on your product rather than the RAG. Easy integration in existing products with customisation! Any LLM: GPT4, Groq, Llama. Any Vectorstore:...
Langchain-Chatchat๏ผๅLangchain-ChatGLM๏ผๅบไบ Langchain ไธ ChatGLM, Qwen ไธ Llama ็ญ่ฏญ่จๆจกๅ็ RAG ไธ Agent ๅบ็จ | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and Ll...
Easily train a good VC model with voice data <= 10 mins!
Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI ...
๐ค Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.
The official Meta Llama 3 GitHub site
๐ฆ Repomix is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for when you need to feed your codebase to Large Language Models (LLMs) or other AI tools like ...
A one stop repository for generative AI research updates, interview resources, notebooks and much more!
The open source AI engineering platform for agents, LLMs, and ML models. MLflow enables teams of all sizes to debug, evaluate, monitor, and optimize production-quality AI applications while controllin...
Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
๐ค The largest hub of ready-to-use datasets for AI models with fast, easy-to-use and efficient data manipulation tools
The official repo of Qwen (้ไนๅ้ฎ) chat & pretrained large language model proposed by Alibaba Cloud.
๐ฌ Open source machine learning framework to automate text- and voice-based conversations: NLU, dialogue management, connect to Slack, Facebook, and more - Create chatbots and voice assistants
Train transformer language models with reinforcement learning.
Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model f...
Private AI platform for agents, assistants and enterprise search. Built-in Agent Builder, Deep research, Document analysis, Multi-model support, and API connectivity for agents.