Open Source
Explore the latest AI open-source projects from GitHub and HuggingFace.
Explore the latest AI open-source projects from GitHub and HuggingFace.
llama.cpp is a pure C/C++ LLM inference engine with no external dependencies, enabling high-performance local inference across a wide range of hardware. It supports Apple Silicon via Metal, NVIDIA CUDA, AMD ROCm, Intel SYCL, Vulkan, and ARM NEON — from Raspberry Pi 5 boards to multi-GPU servers. In March 2026, it crossed 100,000 GitHub stars, making it the fastest open-source AI project to reach that milestone, with over 700 contributors and 3,800+ merged pull requests in 2025 alone.
ollama
The simplest way to run LLMs locally with 165K+ GitHub stars. One-command deployment, 100+ models, REST API, and multi-platform support.
sgl-project
High-performance LLM and multimodal model serving framework with RadixAttention and structured generation.
mlc-ai
Universal LLM deployment engine using ML compilation for cloud, mobile, and web
mlc-ai
Run LLMs entirely in the browser with WebGPU acceleration and OpenAI API compatibility — no server needed