A high-throughput and memory-efficient inference and serving engine for LLMs

Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.

The definitive Web UI for local AI, with powerful features and easy setup.

Distributed Task Queue (development branch)

Data validation using Python type hints

Data Apps & Dashboards for Python. No JavaScript Required.

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.

A curated list of awesome commands, files, and workflows for Claude Code

A powerful coding agent toolkit providing semantic retrieval and editing capabilities (MCP server & other integrations)

DALL·E Mini - Generate images from a text prompt

GenAI Agent Framework, the Pydantic way

A hyperparameter optimization framework

fsociety Hacking Tools Pack – A Penetration Testing Framework

Build better UIs faster.

Simultaneous speech-to-text model

Accessible large language models via k-bit quantization for PyTorch.

An interactive NVIDIA-GPU process viewer and beyond, the one-stop solution for GPU process management.

Plug in and Play Implementation of Tree of Thoughts: Deliberate Problem Solving with Large Language Models that Elevates Model Reasoning by atleast 70%

🌎 Simple and ready-to-use tutorials for TensorFlow

Python Socket.IO server and client

A python module to repair invalid JSON from LLMs

Python package for easily interfacing with chat apps, with robust features and minimal code complexity.

A minimalist environment for decision-making in autonomous driving

Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/

AI conversations that actually remember. Never re-explain your project to Claude again. Local-first, integrates with Obsidian. Join our Discord: https://discord.gg/tyvKNccgqN

Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable. https://docs.kidger.site/diffrax/

Type annotations and runtime checking for shape and dtype of JAX/NumPy/PyTorch/etc. arrays. https://docs.kidger.site/jaxtyping/

A standard framework for modelling Deep Learning Models for tabular data

An intuitive and low-overhead instrumentation tool for Python

Keras/Pytorch implementation of N-BEATS: Neural basis expansion analysis for interpretable time series forecasting.