1.rasbt / LLMs-from-scratch
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
- gpt
- large-language-models
- llm
- python
- pytorch
- ai
- +13 more
Ranked by Attention Score: stars gained over the last 30 complete days
1–100 of 187 by Attention Score · Oct 4, 2026 – Nov 2, 2026 (UTC)
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
🪢 Open source agent evals & observability: Trace, evaluate, and improve LLM applications with one open platform.
Tensors and Dynamic neural networks in Python with strong GPU acceleration
WeFlow - 一个本地的微信聊天记录导出和年度报告应用
1,324-exercise fitness dataset — animation GIFs, 180×180 thumbnails, muscle-group & equipment data, and step-by-step instructions in 6 languages. The exercise data layer behind the LogPress app.
The flexible backend for all your projects 🐰 Turn your DB into a headless CMS, admin panels, or apps with a custom UI, instant APIs, auth & more.
For developers, who are building real-time data-driven applications, Redis is the preferred, fastest, and most feature-rich cache, data structure server, and document and vector query engine.
The easy-to-use open source Business Intelligence and Embedded Analytics tool that lets everyone work with data :bar_chart:
A clinical decision-evidence benchmark: pull the one fact an answer rests on, and see whether the assistant's action moves with the evidence. Built on HealthBench.
This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial.
:hedgehog: PostHog is the leading platform for building self-driving products. Our developer tools – AI observability, analytics, session replay, flags, experiments, error tracking, logs, and more – capture all the context agents need to diagnose problems, uncover opportunities, and ship fixes. Steer it all from Slack, web, desktop, or the MCP.
Don't memorize ML. Understand it from first principles including Inference, Cuda, Deep Learning, Data Science and Reinforcement Learning
AI Observability & Evaluation
50+ tutorials and implementations for Generative AI Agent techniques, from basic conversational bots to complex multi-agent systems.
End-to-end, code-first tutorials for building production-grade GenAI agents. From prototype to enterprise deployment.
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑🔬
GenBI (Generative BI) for AI agents, an open-source, governed text-to-SQL through an open context layer that turns natural-language questions into trusted dashboards, charts, and SQL across 20+ data sources, such as BigQuery, Snowflake, PostgreSQL, ClickHouse, Amazon Redshift, Databricks and more.
Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.
📊 Path to a free self-taught education in Data Science!
📊 Cube Core is open-source semantic layer for AI, BI and embedded analytics
Reference PyTorch implementation and models for DINOv3
Session replay, cobrowsing and product analytics you can self-host. Best for reproducing issues and iterating on your product.
All-in-one IoT Platform - Device management, data collection, processing and visualization.
Open-source data movement for ELT pipelines and AI agents — from APIs, databases & files to warehouses, lakes, and AI applications. Both self-hosted and Cloud.
Open3D: A Modern Library for 3D Data Processing
🔥 人人可用的开源 BI 工具,数据可视化神器。An open-source BI tool alternative to Tableau.
A latent text-to-image diffusion model
强化学习中文教程(蘑菇书🍄),在线阅读地址:https://datawhalechina.github.io/easy-rl/
Chat with your database or your datalake (SQL, CSV, parquet). PandasAI makes data analysis conversational using LLMs and RAG.
Anthropic's educational courses
A powerful tool for creating datasets for LLM fine-tuning 、RAG and Eval
The fastai book, published as Jupyter Notebooks
Materials and IPython notebooks for "Python for Data Analysis" by Wes McKinney, published by O'Reilly Media
Open Source Feature Flags, Experimentation, and Product Analytics
An open access book on scientific visualization using python and matplotlib
Count your code, quickly.
《李宏毅深度学习教程》(李宏毅老师推荐👍,苹果书🍎),PDF下载地址:https://github.com/datawhalechina/leedl-tutorial/releases
Kalman Filter book using Jupyter Notebook. Focuses on building intuition and experience, not formal proofs. Includes Kalman filters,extended Kalman filters, unscented Kalman filters, particle filters, and more. All exercises include solutions.
Agentic BI. Analytics at the speed of code ⚡️
The best JavaScript Data Table for building Enterprise Applications. Supports React / Angular / Vue / Plain JavaScript.
:zap: A Fast, Extensible Progress Bar for Python and CLI
Data science Python notebooks: Deep learning (TensorFlow, Theano, Caffe, Keras), scikit-learn, Kaggle, big data (Spark, Hadoop MapReduce, HDFS), matplotlib, pandas, NumPy, SciPy, Python essentials, AWS, and various command lines.
Open Machine Learning Course
A large collection of system log datasets for AI-driven log analytics [ISSRE'23]
No description provided by the repository host.
A Modular Optimization framework for Localization and mApping (MOLA)
Kedro is a toolbox for production-ready data science. It uses software engineering best practices to help you create data engineering and data science pipelines that are reproducible, maintainable, and modular.
Foundational Models for State-of-the-Art Speech and Text Translation
A curated list of awesome data visualization libraries and resources.
📊 Interactive JavaScript Charts built on SVG
An implementation of the Grammar of Graphics in R
Your new Mentor for Data Science E-Learning.
🔥 A well-tested feature-rich modular Firebase implementation for React Native. Supports both iOS & Android platforms for all Firebase services.
mal - Make a Lisp
Blazing-fast, Neuro-symbolic Data-Wrangling toolkit
TensorFlow Tutorial and Examples for Beginners (support TF v1 & v2)
FCC China open source codebase and curriculum. Learn to code and help nonprofits.
Investigate malicious Windows logon by visualizing and analyzing Windows event log
A neural network that transforms a design mock-up into a static website.
🔩 Like builtins, but boltons. 250+ constructs, recipes, and snippets which extend (and rely on nothing but) the Python standard library. Nothing like Michael Bolton.
Python audio and music signal processing library
Countly is a privacy-first, AI-powered analytics and engagement platform for understanding and optimizing customer journeys across digital applications, from desktop and mobile to IoT and connected environments.
Easy interactive web applications with R
:orange_book: The probability and statistics cookbook
TorchXRayVision: A library of chest X-ray datasets and models. Classifiers, segmentation, and autoencoders.
Pathology Foundation Model - Nature Medicine
Open-source, low-code AutoML platform for Python. PyCaret 4.0: sklearn-native engine + React control plane.
Multi-language suite for high-performance solvers of differential equations and scientific machine learning (SciML) components. Ordinary differential equations (ODEs), stochastic differential equations (SDEs), delay differential equations (DDEs), differential-algebraic equations (DAEs), and more in Julia.
An extensible framework for linking databases and interactive views.
WebGL accelerated JavaScript molecular graphics library
React friendly API wrapper around MapboxGL JS
Statistical Machine Intelligence & Learning Engine
Voilà turns Jupyter notebooks into standalone web applications
Lightweight and modular C++11 graphics middleware for games and data visualization
Fast data visualization and GUI tools for scientific / engineering applications
HOMER - 100% Open-Source SIP, VoIP, RTC Packet Capture & Monitoring
WFGY is heading toward WFGY 5.0 Polaris Protocol, a major open-source release for AI reasoning, RAG, agents, and real-world workflows. Includes Problem Map, Global Debug Card, WFGY 4.0, and the CFV Easter Egg.
High-performance Toolkit for WebGL-based Data Visualization
GRASS - free and open-source geospatial processing engine
Foundation Models for Genomics & Transcriptomics
A library of extension and helper modules for Python's data analysis and machine learning libraries.
Deepchecks: Tests for Continuous Validation of ML Models & Data. Deepchecks is a holistic open-source solution for all of your AI & ML validation needs, enabling to thoroughly test your data and models from research to production.
A lightweight, cross-platform, portable, and easy-to-maintain LaTeX distribution based on TeX Live
A collection of composable React components for building interactive data visualizations
Python Data. Leaflet.js Maps.
Algorithms for outlier, adversarial and drift detection
Graph and network visualization using tabular data in R
Keep code, data, containers under control with git and git-annex
JQuick-Pdf is an enterprise-grade Java PDF generation framework. It provides HTML-like declarative syntax and supports more than 30 kinds of graphs, greatly simplifying complex PDF report creation while retaining full native pdfbox(since version 4.0.0) APIs.
The Udacity open source self-driving car project