A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

Bridging the gap between jupyter notebooks and text editors/IDEs

Debug your python script with a jupyter notebook

NeurIPS 2025

Tools for merging pretrained large language models.

[CSUR 2025] Continual Learning of Large Language Models: A Comprehensive Survey

GPU environment and cluster management with LLM support

PyTorch native post-training library

Browser MCP is a Model Context Provider (MCP) server that allows AI applications to control your browser

An open-source AI agent that brings the power of Gemini directly into your terminal.

A powerful GUI app and Toolkit for Claude Code - Create custom agents, manage interactive Claude Code sessions, run secure background agents, and more.

Avalanche: an End-to-End Library for Continual Learning based on PyTorch.

[ICML 2024] SINGD: KFAC-like Structured Inverse-Free Natural Gradient Descent (http://arxiv.org/abs/2312.05705)

Jan is an open source alternative to ChatGPT that runs 100% offline on your computer.

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

An Open Source implementation of Notebook LM with more flexibility and features

This is to enable 60fps and GPU acceleration on RDP connection

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

[ICLR 2024] - Elastic Feature Consolidation for Cold Start Exemplar-Free Incremental Learning

BackPACK - a backpropagation package built on top of PyTorch which efficiently computes quantities other than the gradient.

Matplotlib styles for scientific plotting

Implementation of all RL algorithms in a simpler way

Deep reinforcement learning without experience replay, target networks, or batch updates.

A new kind of Progress Bar, with real-time throughput, ETA, and very cool animations!

🪄 Create rich visualizations with AI

Code for the paper "Slow and Steady Wins the Race: Maintaining Plasticity with Hare and Tortoise Networks" (ICML 2024)

AlphaFold 3 inference pipeline.

Get up and running with Kimi-K2.6, GLM-5.1, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks