Open Source
Explore the latest AI open-source projects from GitHub and HuggingFace.
Explore the latest AI open-source projects from GitHub and HuggingFace.
MLC-AI's high-performance in-browser LLM inference engine that runs large language models entirely in the web browser using WebGPU hardware acceleration, with no server required. WebLLM is fully compatible with the OpenAI API, supporting streaming, JSON mode, and function calling for local privacy-preserving inference. Models are cached in the browser after first download, enabling offline operation. Supports Llama 3.2, Phi-4, Gemma 2, Mistral, Qwen 2.5, and DeepSeek-R1 distilled variants.
ollama
The simplest way to run LLMs locally with 165K+ GitHub stars. One-command deployment, 100+ models, REST API, and multi-platform support.
ggml-org
Pure C/C++ LLM inference engine supporting CPUs, Apple Silicon, CUDA, and Vulkan
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