HTML to markdown converter

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

GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.

LlamaIndex is the leading framework for building LLM-powered agents over your data.

bluetooth mesh chat, IRC vibes

🦀 How to minimize Rust binary size 📦

container images for C++ CI workflows

Opensource IDE For Exploring and Testing API's (lightweight alternative to Postman/Insomnia)

matrix multiplication in CUDA

Get your documents ready for gen AI

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

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

Ecosystem of libraries and tools for writing and executing fast GPU code fully in Rust.

Perforator is a cluster-wide continuous profiling tool designed for large data centers

Log file navigator

🌀 A log file highlighter

A TUI for reading logs from journald, auditd, file system, Docker containers, Compose stacks, Podman and Kubernetes pods with support for output coloring and multiple filtering modes.

🌐 Make websites accessible for AI agents. Automate tasks online with ease.

Writing an OS in 1,000 lines.

LLM training in simple, raw C/CUDA

Inference Llama 2 in one file of pure C

The simplest, fastest repository for training/finetuning medium-sized GPTs.

A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API

PyTorch Tutorial for Deep Learning Researchers

⏩ Ship faster with Continuous AI. Open-source CLI that can be used in TUI mode as a coding agent or Headless mode to run background agents

Get up and running with OpenAI gpt-oss, DeepSeek-R1, Gemma 3 and other models.