Trending reposUpdated daily from GitHub
Curated GitHub repos: standout and rising.
Curated GitHub repos: standout and rising.
| # | Repo |
|---|---|
| 5051 | Inactive (no push for over a year, or archived)mit-han-lab/TinyChatEngine TinyChatEngine: On-Device LLM Inference Library 974—C++ LLM & foundation models |
| 5052 | Inactive (no push for over a year, or archived)sekwiatkowski/awesome-capsule-networksDocs A curated list of awesome resources related to capsule networks 974— Training & fine-tuning |
| 5053 | Active (pushed in the last 90 days)mir-group/nequip NequIP is a code for building E(3)-equivariant interatomic potentials 974—Python Training & fine-tuning |
| 5054 | Active (pushed in the last 90 days)TryCaspian/caspian-sdk Agent communication SDK. The open-source agent communication layer for AI agents — email, WhatsApp, Slack, Discord, Telegram, SMS. Python & TypeScript. 973—Python Agent frameworks |
| 5055 | Inactive (no push for over a year, or archived)ECNU-ICALK/EduChat An open-source educational chat model from ICALK, East China Normal University. 开源中英教育对话大模型。(通用基座模型，GPU部署，数据清理) 致敬: LLaMA, MOSS, BELLE, Ziya, vLLM 973—Jupyter Notebook LLM & foundation models |
| 5056 | Slowing down (last push 3–12 months ago)kessler/gemma-gem Gemma Gem runs Google's Gemma 4 model entirely on-device via WebGPU — no API keys, no cloud, no data leaving your machine. 973—TypeScript LLM & foundation models |
| 5057 | Slowing down (last push 3–12 months ago)bansalkanav/Ultimate-Data-Science-Toolkit---From-Python-Basics-to-GenerativeAI 973—Jupyter Notebook LLMOps & evaluation |
| 5058 | Inactive (no push for over a year, or archived)konpatp/diffae Official implementation of Diffusion Autoencoders 973—Jupyter Notebook Training & fine-tuning |
| 5059 | Inactive (no push for over a year, or archived)DmitryRyumin/ICCV-2023-25-Papers ICCV 2023-2025 Papers: Discover cutting-edge research from ICCV 2023-25, the leading computer vision conference. Stay updated on the latest in computer vision and deep learning, with code included. ⭐ support visual intelligence development! 972—Python Computer vision |
| 5060 | Inactive (no push for over a year, or archived)kennethleungty/Llama-2-Open-Source-LLM-CPU-Inference Running Llama 2 and other Open-Source LLMs on CPU Inference Locally for Document Q&A 972—Python LLM & foundation models |
| 5061 | Active (pushed in the last 90 days)Electricitysheep/dsh-handbookDocs DeepSeek Harness (dsh) 从 0 到 1 深度手册：安装/插件开发/性能调优/实测案例/同模型多 Agent 实测对比（中文 + 英文 PDF） 972—HTML LLM & foundation models |
| 5062 | Slowing down (last push 3–12 months ago)rasbt/MachineLearning-QandAI-book Machine Learning Q and AI book 972—Jupyter Notebook Training & fine-tuning |
| 5063 | Inactive (no push for over a year, or archived)DataXujing/YOLO-v5 :art: Pytorch YOLO v5 训练自己的数据集超详细教程！！！ :art: (提供PDF训练教程下载） 972—Jupyter Notebook Training & fine-tuning |
| 5064 | Active (pushed in the last 90 days)lkimuk/ReArk An intelligent reverse engineering and AI-assisted analysis tool for HarmonyOS NEXT (HAP/APP/ABC), Android (APK/AAB), iOS (IPA), and native PE/ELF/Mach-O binaries. 970—C++ Agent frameworks |
| 5065 | Inactive (no push for over a year, or archived)mit-han-lab/tinyengine [NeurIPS 2020] MCUNet: Tiny Deep Learning on IoT Devices; [NeurIPS 2021] MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning; [NeurIPS 2022] MCUNetV3: On-Device Training Under 256KB Memory 970—C Training & fine-tuning |
| 5066 | Inactive (no push for over a year, or archived)Denis2054/Transformers-for-NLP-2nd-Edition Transformer models from BERT to GPT-4, environments from Hugging Face to OpenAI. Fine-tuning, training, and prompt engineering examples. A bonus section with ChatGPT, GPT-3.5-turbo, GPT-4, and DALL-E including jump starting GPT-4, speech-to-text, text-to-speech, text to image generation with DALL-E, Google Cloud AI,HuggingGPT, and more 970—Jupyter Notebook Training & fine-tuning |
| 5067 | Inactive (no push for over a year, or archived)huawei-noah/AdderNet Code for paper " AdderNet: Do We Really Need Multiplications in Deep Learning?" 970—Python Training & fine-tuning |
| 5068 | Active (pushed in the last 90 days)dromara/dante-cloud 🐉 Dante Cloud 是支持阻塞式与响应式服务并行的微服务云原生基座和面向AI Agent开发的智能基座，基于领域驱动模型（DDD）设计，以高质量代码与低安全漏洞为核心，高度模块化、组件化，覆盖IoT设备认证、国家等保三级、接口国密数字信封加密等多层次安全体系，并提供多租户解决方案。独创“一套代码实现微服务和单体架构灵活切换”，赋能企业级智能应用构建。🔝🔝点个star 持续关注更新！ 969—Java Agent frameworks |
| 5069 | Active (pushed in the last 90 days)openeverest/openeverest OpenEverest is an open-source platform for automated database, storage and LLMs provisioning and management. It supports multiple technologies and can be hosted on any Kubernetes infrastructure, in the cloud or on-premises. 969—TypeScript LLM & foundation models |
| 5070 | Active (pushed in the last 90 days)data-prep-kit/data-prep-kit Open source project for data preparation for GenAI applications 969—HTML LLM & foundation models |
| 5071 | Slowing down (last push 3–12 months ago)OpenGVLab/OmniQuant [ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs. 969—Python LLM & foundation models |
| 5072 | Active (pushed in the last 90 days)mbzuai-oryx/groundingLMM [CVPR 2024 🔥] Grounding Large Multimodal Model (GLaMM), the first-of-its-kind model capable of generating natural language responses that are seamlessly integrated with object segmentation masks. 969—Python LLM & foundation models |
| 5073 | Active (pushed in the last 90 days)AgileRL/AgileRL The complete post-training stack for LLMs, plus RL for any problem. SFT, DPO and multi-turn agentic RL, with evolutionary hyperparameter optimization built in. 968—Python LLM & foundation models |
| 5074 | Active (pushed in the last 90 days)papercopilot/paperlists Processed / Cleaned Data for Paper Copilot 967—Python Computer vision |
| 5075 | Active (pushed in the last 90 days)dalisoft/awesome-hostingDocs List of awesome hosting sorted by minimal plan price 967— LLM & foundation models |
| 5076 | Slowing down (last push 3–12 months ago)rezaakb/pinns-torch PINNs-Torch, Physics-informed Neural Networks (PINNs) implemented in PyTorch. 967—Python Training & fine-tuning |
| 5077 | Active (pushed in the last 90 days)kardolus/chatgpt-cli ChatGPT CLI is a powerful, multi-provider command-line interface for working with modern LLMs. It supports OpenAI, Azure, Perplexity, LLaMA, and more, with features like streaming, interactive chat, prompt files, image/audio I/O, MCP tool calls, and an experimental agent mode for safe, multi-step automation. 966—Go Chat apps & assistants |
| 5078 | Inactive (no push for over a year, or archived)horseee/DeepCache [CVPR 2024] DeepCache: Accelerating Diffusion Models for Free 966—Python Image generation |
| 5079 | Active (pushed in the last 90 days)s0ld13rr/pentestcode PentestCode - Multi-agent AI penetration testing system with persistent engagement state, strategic coordination, and parallel autonomous operations. 965—TypeScript Agent frameworks |
| 5080 | Slowing down (last push 3–12 months ago)hmans/beans A CLI-based, flat-file issue tracker for humans and robots. 🤖 965—Go Agent frameworks |
| 5081 | Slowing down (last push 3–12 months ago)huifer/WellAlly-health Ally-Health is an intelligent healthcare assistant that harnesses advanced AI technology and medical expertise to transform personal health management. Through natural language interaction, it helps users record symptoms, manage medications, organize medical records, and access multidisciplinary health insights—making healthcare more intelligent, p 965—Shell Chat apps & assistants |
| 5082 | Inactive (no push for over a year, or archived)Cartucho/OpenLabeling Label images and video for Computer Vision applications 965—Python Computer vision |
| 5083 | Inactive (no push for over a year, or archived)ZhUyU1997/open-pose-editor online 3d openpose editor for stable diffusion and controlnet 964—TypeScript Image generation |
| 5084 | Inactive (no push for over a year, or archived)princeton-nlp/SimPO [NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward 964—Python LLM & foundation models |
| 5085 | Inactive (no push for over a year, or archived)WisconsinAIVision/MixNMatch Pytorch implementation of MixNMatch 964—Python Training & fine-tuning |
| 5086 | Slowing down (last push 3–12 months ago)inngest/agent-kit AgentKit: Build multi-agent networks in TypeScript with deterministic routing and rich tooling via MCP. 963—TypeScript Agent frameworks |
| 5087 | Inactive (no push for over a year, or archived)RapidAI/TableStructureRec 整理目前开源的最优表格识别模型，完善前后处理，模型转换为ONNX | Organize the currently open-source optimal table recognition models, improve pre-processing and post-processing, and convert the models to ONNX. 963—Python Computer vision |
| 5088 | Slowing down (last push 3–12 months ago)dropbox/hqq Official implementation of Half-Quadratic Quantization (HQQ) 963—Python Inference & local LLM |
| 5089 | Active (pushed in the last 90 days)qinshihu/itops-agent-platform China's 1st enterprise multi-agent IT ops platform. LLM-powered auto-remediation for Zabbix/Prometheus. Docker deploy. 962—TypeScript Agent frameworks |
| 5090 | Active (pushed in the last 90 days)im4codes/imcodes The IM for agents. Shared Agent Context & Memory, supervised execution, and cross-agent audit across AI providers. 962—TypeScript Chat apps & assistants |
| 5091 | Active (pushed in the last 90 days)kossakovsky/selfhost-ai One-command installer for a self-hosted AI stack on your own server: n8n, Ollama, Open WebUI, OpenClaw, Dify, Flowise, Supabase, ComfyUI, Qdrant & 30+ tools. Docker Compose, automatic HTTPS via Caddy, built-in monitoring. Free Zapier/Make alternative. 962—Shell Inference & local LLM |
| 5092 | Active (pushed in the last 90 days)feder-cr/jev jevos: an open-source alternative to Jev and Microsoft-Decision-1. Yes/no decisions, choices and scores with probabilities, on your laptop's CPU. 962—C++ Inference & local LLM |
| 5093 | Inactive (no push for over a year, or archived)VincentStimper/normalizing-flows PyTorch implementation of normalizing flow models 962—Python Training & fine-tuning |
| 5094 | Inactive (no push for over a year, or archived)easezyc/deep-transfer-learning A collection of implementations of deep domain adaptation algorithms 962—Python Training & fine-tuning |
| 5095 | Active (pushed in the last 90 days)dezoito/ollama-grid-search A multi-platform desktop application to evaluate and compare LLM models, written in Rust and React. 961—TypeScript LLM & foundation models |
| 5096 | Active (pushed in the last 90 days)weiwill88/Local_Pdf_Chat_RAG Transparent Python RAG reference with FAISS + BM25 hybrid retrieval, reranking, Gradio UI, and FastAPI. 961—Python RAG, memory & search |
| 5097 | Active (pushed in the last 90 days)Raudaschl/rag-fusion RAG-Fusion: multi-query generation + Reciprocal Rank Fusion for better retrieval-augmented generation. Includes evaluation harness with NFCorpus/BEIR. 961—Python RAG, memory & search |
| 5098 | Active (pushed in the last 90 days)cvg/GeoCalib GeoCalib: Learning Single-image Calibration with Geometric Optimization (ECCV 2024) 961—Python Training & fine-tuning |
| 5099 | Slowing down (last push 3–12 months ago)pkoukk/tiktoken-go go version of tiktoken 960—Go Chat apps & assistants |
| 5100 | Slowing down (last push 3–12 months ago)kujason/avod Code for 3D object detection for autonomous driving 960—Python Computer vision |