The best ChatGPT that $100 can buy.

The AI coding agent built for the terminal.

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

Continuous Thought Machines, because thought takes time and reasoning is a process.

Containerization is a Swift package for running Linux containers on macOS.

An extremely fast Python type checker and language server, written in Rust.

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

Lightweight coding agent that runs in your terminal

s1: Simple test-time scaling

Code extension that allows you to easily copy file and folder contents along with the project tree structure to your clipboard

Leaderboard Comparing LLM Performance at Producing Hallucinations when Summarizing Short Documents

Hallucinations (Confabulations) Document-Based Benchmark for RAG. Includes human-verified questions and answers.

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

Janus-Series: Unified Multimodal Understanding and Generation Models

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

The Gameboy emulator that runs everywhere (Terminal, Web, Desktop)

Blazingly fast LLM inference.

A secure container runtime with CRI/OCI interface

Open source real-time translation app for Android that runs locally

LiveBench: A Challenging, Contamination-Free LLM Benchmark

Kolmogorov Arnold Networks

Zero-Shot Speech Editing and Text-to-Speech in the Wild

Universal LLM Deployment Engine with ML Compilation

Stable Diffusion implementation using CoreML, PyTorch and SwiftUI

MoltenVK is a Vulkan Portability implementation. It layers a subset of the high-performance, industry-standard Vulkan graphics and compute API over Apple's Metal graphics framework, enabling Vulkan…

Minimalist ML framework for Rust

Verify apps easily.

Open-source Windows and Office activator featuring HWID, Ohook, TSforge, and Online KMS activation methods, along with advanced troubleshooting.