Trending AI reposUpdated daily from GitHub
AI, coding & video AI repos ranked by star growth.
AI, coding & video AI repos ranked by star growth.
| # | Repo | Stars | 7d |
|---|---|---|---|
| 1 | NO nomic-ai/gpt4all GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use. Inference & local LLM | 77.3K | — |
| 2 | 1P 1Panel-dev/1Panel 🔥 1Panel is a modern, open-source Linux server management panel and a lightweight AI management platform. 1Panel 是专门为 AI 服务器打造的管理面板。 Inference & local LLM | 37.4K | — |
| 3 | SY | 26.7K | — |
| 4 | MO | 26.6K | — |
| 5 | UF UFund-Me/Qbot [🔥updating ...] AI 自动量化交易机器人(完全本地部署) AI-powered Quantitative Investment Research Platform. 📃 online docs: https://ufund-me.github.io/Qbot ✨ :news: qbot-mini: https://github.com/Charmve/iQuant Inference & local LLM | 18.8K | — |
| 6 | FL FlashML-org/FreeToken FreeToken brings datacenter-scale model serving to your desktop. Run massive models locally, fast and efficiently. Inference & local LLM | 17.1K | — |
| 7 | GV gvergnaud/ts-pattern 🎨 The exhaustive Pattern Matching library for TypeScript, with smart type inference. Inference & local LLM | 15.2K | — |
| 8 | NV NVIDIA/TensorRT NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT. Inference & local LLM | 13.5K | — |
| 9 | FA FareedKhan-dev/kimi-k3-in-c A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU. Inference & local LLM | 12K | — |
| 10 | OP openvinotoolkit/openvino OpenVINO™ is an open source toolkit for optimizing and deploying AI inference Inference & local LLM | 11.2K | — |
| 11 | TR triton-inference-server/server The Triton Inference Server provides an optimized cloud and edge inferencing solution. Inference & local LLM | 11.1K | — |
| 12 | AW aws/amazon-sagemaker-examples Example 📓 Jupyter notebooks that demonstrate how to build, train, and deploy machine learning models using 🧠 Amazon SageMaker. Inference & local LLM | 11K | — |
| 13 | HU huggingface/text-generation-inference(archived) Large Language Model Text Generation Inference Inference & local LLM | 10.9K | — |
| 14 | MI mistralai/mistral-inference(archived) Official inference library for Mistral models Inference & local LLM | 10.8K | — |
| 15 | OL | 10.7K | — |
| 16 | RU | 10.3K | — |
| 17 | LE LearningCircuit/local-deep-research ~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private documents. Everything Local & Encrypted. Inference & local LLM | 9.6K | — |
| 18 | MI | 9.3K | — |
| 19 | DU dusty-nv/jetson-inference Hello AI World guide to deploying deep-learning inference networks and deep vision primitives with TensorRT and NVIDIA Jetson. Inference & local LLM | 9K | — |
| 20 | AI | 8.5K | — |
| 21 | N4 n4ze3m/page-assist Use your locally running AI models to assist you in your web browsing Inference & local LLM | 8.3K | — |
| 22 | LI Linzaer/Ultra-Light-Fast-Generic-Face-Detector-1MB 💎1MB lightweight face detection model (1MB轻量级人脸检测模型) Inference & local LLM | 7.6K | — |
| 23 | DR drumih/turbo-fieldfare Gemma 4 26B-A4B inference in ~2 GB of RAM on any M-series MacBook Inference & local LLM | 7.3K | — |
| 24 | MI mizorewww/laya-mlx Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API. Inference & local LLM | 7.1K | — |
| 25 | FL | 6.9K | — |
| 26 | GC | 6.8K | — |
| 27 | TE tensorflow/serving A flexible, high-performance serving system for machine learning models Inference & local LLM | 6.4K | — |
| 28 | TR Trusted-AI/adversarial-robustness-toolbox Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference - Red and Blue Teams Inference & local LLM | 6.3K | — |
| 29 | KS kserve/kserve Standardized Distributed Generative and Predictive AI Inference Platform for Scalable, Multi-Framework Deployment on Kubernetes Inference & local LLM | 6.2K | — |
| 30 | MI Michael-A-Kuykendall/shimmy ⚡ Pure-Rust WebGPU inference engine — OpenAI-API compatible, GGUF native, runs on any GPU. No Python. No llama.cpp. Single binary. Inference & local LLM | 6K | — |
| 31 | KO kornelski/pngquant Lossy PNG compressor — pngquant command based on libimagequant library Inference & local LLM | 5.8K | — |
| 32 | AI AienTech/dossier A self-hosted job search and resume builder app that writes tailored resumes and cover letters from your profile. Inference & local LLM | 5.1K | — |
| 33 | AU AutoGPTQ/AutoGPTQ(archived) An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm. Inference & local LLM | 5.1K | — |
| 34 | NV | 4.9K | — |
| 35 | VI vinta/pangu.js Opinionated paranoid text spacing in JavaScript, with on-device AI semantic judgment Inference & local LLM | 4.9K | — |
| 36 | OP | 4.7K | — |
| 37 | RU ruvnet/RuVector RuVector provides High Performance, Real-Time decisions and agent memory , Self-Learning Ai, Vector GNN DB built in Rust. Inference & local LLM | 4.7K | — |
| 38 | TY | 4.5K | — |
| 39 | OP openvinotoolkit/open_model_zoo Pre-trained Deep Learning models and demos (high quality and extremely fast) Inference & local LLM | 4.4K | — |
| 40 | OL | 4.4K | — |
| 41 | ZM zml/zml Any model. Any hardware. Zero compromise. Built with @ziglang / @openxla / MLIR / @bazelbuild Inference & local LLM | 4.3K | — |
| 42 | RA raullenchai/Rapid-MLX Rapid-MLX is an open-source (Apache 2.0) OpenAI- and Anthropic-compatible LLM inference server for Apple Silicon, built on MLX, focused on reliable tool calling for coding agents. Up to 4× faster than Apple's MLX (mlx-lm) on the same weights. Inference & local LLM | 4.1K | — |
| 43 | TH thu-ml/SageAttention [ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models. Inference & local LLM | 4K | — |
| 44 | VL vllm-project/llm-compressor State-of-the-art LLM compression, built for production inference with vLLM Inference & local LLM | 4K | — |
| 45 | NU nunchux-ai/nunchaku [ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models Inference & local LLM | 4K | — |
| 46 | AT AtomicBot-ai/atomic-agent Atomic Agent is a local-first AI agent. Runs open-weight models on your own machine via llama.cpp. Inference & local LLM | 3.7K | — |
| 47 | AM amitshekhariitbhu/ai-engineering-interview-questions Your Cheat Sheet for AI Engineering Interview – Questions and Answers. Inference & local LLM | 3.6K | — |
| 48 | HU huggingface/optimum 🚀 Accelerate inference and training of 🤗 Transformers, Diffusers, TIMM and Sentence Transformers with easy to use hardware optimization tools Inference & local LLM | 3.5K | — |
| 49 | TR | 3.3K | — |
| 50 | BY bytedance/lightseq(archived) LightSeq: A High Performance Library for Sequence Processing and Generation Inference & local LLM | 3.3K | — |