Trending reposUpdated daily from GitHub
Curated GitHub repos: standout and rising.
Curated GitHub repos: standout and rising.
| # | Repo |
|---|---|
| 4451 | Inactive (no push for over a year, or archived)IST-DASLab/marlin FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens. 1.2K—Python LLM & foundation models |
| 4452 | Active (pushed in the last 90 days)uncbiag/Awesome-Foundation-ModelsDocs A curated list of foundation models for vision and language tasks 1.2K— LLM & foundation models |
| 4453 | Inactive (no push for over a year, or archived)weaveworks/kubediff(archived) Kubediff: a tool for Kubernetes to show differences between running state and version controlled configuration. 1.2K—Python LLMOps & evaluation |
| 4454 | Slowing down (last push 3–12 months ago)iver56/torch-audiomentations Fast audio data augmentation in PyTorch. Inspired by audiomentations. Useful for deep learning. 1.2K—Python Training & fine-tuning |
| 4455 | Inactive (no push for over a year, or archived)shadow2496/VITON-HD Official PyTorch implementation of "VITON-HD: High-Resolution Virtual Try-On via Misalignment-Aware Normalization" (CVPR 2021) 1.2K—Python Training & fine-tuning |
| 4456 | Active (pushed in the last 90 days)ys-ll/uniterm All-in-one terminal covering 30+ protocols — SSH, RDP, SFTP, databases, Kubernetes and more. With a built-in AI Agent that runs multi-turn shell commands autonomously. 1.2K—Go Agent frameworks |
| 4457 | Active (pushed in the last 90 days)KroMiose/nekro-agent NekroAgent 是一个面向多人互动场景的跨平台 Agent 框架，集 Claude Code 沙盒执行、工作区编排、长期记忆、结构化 MCP 管理与可视化控制台于一体，兼具高扩展性、多模态交互、实时状态推送和自动化运行能力。项目支持 QQ、Discord、Telegram、Minecraft、BilibiliLive、WeChat、Email、SSE(SDK) 等多种平台接入，应用于构建高智能聊天机器人，可扩展为具备代码执行、工具调用、插件协作和复杂任务处理能力的通用 Agent 系统 1.2K—Python Chat apps & assistants |
| 4458 | Inactive (no push for over a year, or archived)1zilc/fishing-funds(archived) 基金,大盘,股票,虚拟货币状态栏显示小应用 1.2K—TypeScript Chat apps & assistants |
| 4459 | Active (pushed in the last 90 days)chrishayuk/larql Run, serve, query and edit AI models — a Rust model runtime built on VINDEX3, an executable, inspectable model format. 1.2K—Rust LLM & foundation models |
| 4460 | Inactive (no push for over a year, or archived)SuperBruceJia/EEG-DL A Deep Learning library for EEG Tasks (Signals) Classification, based on TensorFlow. 1.2K—Python Training & fine-tuning |
| 4461 | Inactive (no push for over a year, or archived)LibCity/Bigscity-LibCity LibCity: An Open Library for Urban Spatial-temporal Data Mining 1.2K—Python Training & fine-tuning |
| 4462 | Inactive (no push for over a year, or archived)nv-tlabs/LLaMA-Mesh Unifying 3D Mesh Generation with Language Models 1.2K—Python LLM & foundation models |
| 4463 | Active (pushed in the last 90 days)Zleap-AI/SAG-Wiki A lightweight knowledge base for people and agents, with ultra fast indexing and most precise retrieval. 1.2K—Rust RAG, memory & search |
| 4464 | Inactive (no push for over a year, or archived)ermongroup/SDEdit PyTorch implementation for SDEdit: Image Synthesis and Editing with Stochastic Differential Equations 1.2K—Python Training & fine-tuning |
| 4465 | Slowing down (last push 3–12 months ago)whyiyhw/chatgpt-wechat 企业微信/微信 安全使用的 LLM 个人助手/客服, 也支持 dify 工作流 1.2K—Go Chat apps & assistants |
| 4466 | Inactive (no push for over a year, or archived)yuanxiaosc/Machine-Learning-BookDocs 《机器学习宝典》包含：谷歌机器学习速成课程（招式）+机器学习术语表（口诀）+机器学习规则（心得）+机器学习中的常识性问题 （内功）。该资源适用于机器学习、深度学习研究人员和爱好者参考！ 1.2K—Jupyter Notebook Training & fine-tuning |
| 4467 | Inactive (no push for over a year, or archived)ndb796/Deep-Learning-Paper-Review-and-Practice 꼼꼼한 딥러닝 논문 리뷰와 코드 실습 1.2K—Jupyter Notebook Training & fine-tuning |
| 4468 | Slowing down (last push 3–12 months ago)cvg/glue-factory Training library for local feature detection and matching 1.2K—Python Training & fine-tuning |
| 4469 | Inactive (no push for over a year, or archived)GaParmar/clean-fid PyTorch - FID calculation with proper image resizing and quantization steps [CVPR 2022] 1.2K—Python Training & fine-tuning |
| 4470 | Active (pushed in the last 90 days)Muuuun/luxas An autonomous research colleague — from a question to a compiled manuscript, while you sleep. 1.2K—TypeScript Agent frameworks |
| 4471 | Slowing down (last push 3–12 months ago)yandex-research/rtdl Research on Tabular Deep Learning: Papers & Packages 1.2K—Python Training & fine-tuning |
| 4472 | Slowing down (last push 3–12 months ago)patchy631/time-to-first-tokenDocs A 10-week, 30-minutes-a-day roadmap for LLM inference serving and optimization. vLLM, SGLang, quantization, speculative decoding, benchmarking. 1.2K—HTML Inference & local LLM |
| 4473 | Inactive (no push for over a year, or archived)cure-lab/MagicDrive [ICLR24] Official implementation of the paper “MagicDrive: Street View Generation with Diverse 3D Geometry Control” 1.2K—Python Training & fine-tuning |
| 4474 | Slowing down (last push 3–12 months ago)junyanz/CatPapersDocs Cool vision, learning, and graphics papers on Cats! 1.2K—Python Training & fine-tuning |
| 4475 | Active (pushed in the last 90 days)alexandre01/deepsvg [NeurIPS 2020] Official code for the paper "DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation". Includes a PyTorch library for deep learning with SVG data. 1.2K—Jupyter Notebook Training & fine-tuning |
| 4476 | Slowing down (last push 3–12 months ago)oneapi-src/oneAPI-samples Samples for Intel® oneAPI Toolkits 1.2K—C++ Training & fine-tuning |
| 4477 | Slowing down (last push 3–12 months ago)Guru322/GURU-Ai SIMPLE YET COMPLICATED 🚩 1.2K—JavaScript Chat apps & assistants |
| 4478 | Inactive (no push for over a year, or archived)FoundationVision/GLEE [CVPR2024 Highlight]GLEE: General Object Foundation Model for Images and Videos at Scale 1.2K—Python Computer vision |
| 4479 | Active (pushed in the last 90 days)MarkMoHR/Awesome-Image-ColorizationDocs :books: A collection of Deep Learning based Image Colorization and Video Colorization papers. 1.2K— Training & fine-tuning |
| 4480 | Inactive (no push for over a year, or archived)PKU-Alignment/omnisafe JMLR: OmniSafe is an infrastructural framework for accelerating SafeRL research. 1.2K—Python Training & fine-tuning |
| 4481 | Active (pushed in the last 90 days)BoardUI/boardui React design system for agentic interfaces. Every free BoardUI component as source, with a working AI chat app on your own model key as the homepage. 1.2K—TypeScript Agent frameworks |
| 4482 | Inactive (no push for over a year, or archived)rafaelpadilla/review_object_detection_metrics Object Detection Metrics. 14 object detection metrics: mean Average Precision (mAP), Average Recall (AR), Spatio-Temporal Tube Average Precision (STT-AP). This project supports different bounding box formats as in COCO, PASCAL, Imagenet, etc. 1.2K—Python Computer vision |
| 4483 | Inactive (no push for over a year, or archived)18601949127/DiDiCallCar 这是我自己做的一个类似滴滴打车的Android出行项目，主要针对滴滴等出行平台一直饱受质疑的“人车不符”问题，以及当前越发火热的或计划和出海战略，给出行项目增加了下面几个功能： 1. RFID识别验证功能：在司机证件或者车内识别硬件嵌入RFID识别芯片，乘客使用手机读取到芯片信息，并且通过网络发送到出行平台数据库进行验证（我用JNI加了一个C语言的MD5加密算法对识别到的信息进行了加密）。如果不是合规的“人”或“车”，则不能完成订单并向平台或监管单位汇报当前位置。（为了方便读者测试，可以使用手机读取任何一个加密或非加密RFID芯片，比如银行卡、公交卡等，我在代码中的验证前阶段把芯片信息都换成我自己的司机信息，确保读者测试时可以收到服务器的回复） 2. 海外版功能：点击切换当前语言。 3. 司机证件号码识别功能：读取司机证件上的证件号码，也可以用来与出行平台数据库的接单司机信息进行。I complete this whole project on my own . Including Android application programming，web server ( Apache + PHP + MySQL), and UI. 1．Map route planing。You can use mobile phone choose pick up & destination address，application provide address name hint and draw optimized route for user , then call car for you. 2．RFID authentication function：User can use application to scan driver license or other RFID hardware, then use NDK MD5 algorithm encrypt RFID number, and send it to Web Server Database, check with driver information and authenticate ID number , if ID number coherent with driver info , send back driver information to User and continue call car order . record user location and alert if ID not coherent. 3．Driver License Number Recognition : Application can recognize driver license digit number ,and also can send to web server for authentication & feed back result to user. 1.2K—Java Computer vision |
| 4484 | Slowing down (last push 3–12 months ago)PaddleJitLab/CUDATutorial A self-learning tutorail for CUDA High Performance Programing. 1.2K—JavaScript Training & fine-tuning |
| 4485 | Inactive (no push for over a year, or archived)amusi/TensorFlow-From-Zero-To-One TensorFlow 最佳学习资源大全（含课程、书籍、博客、公开课等内容） 1.2K—Jupyter Notebook Training & fine-tuning |
| 4486 | Active (pushed in the last 90 days)gufo-org/gufo The open-source AI engine for AMD Strix Halo. Text, embeddings, speech, image and video models in one binary, with OpenAI-compatible APIs, caching for coding agents and model extensions. Linux and Windows. 1.2K—C++ LLM & foundation models |
| 4487 | Inactive (no push for over a year, or archived)sirius-ai/LPRNet_Pytorch Pytorch Implementation For LPRNet, A High Performance And Lightweight License Plate Recognition Framework. 1.2K—Python Training & fine-tuning |
| 4488 | Active (pushed in the last 90 days)lee-to/ai-factory You want to build with AI, but setting up the right context, prompts, and workflows takes time. AI Factory handles all of that so you can focus on what matters — shipping quality code. 1.2K—JavaScript Agent frameworks |
| 4489 | Inactive (no push for over a year, or archived)abhagsain/ai-cli Get answers for CLI commands from ChatGPT right from your terminal 1.2K—TypeScript Chat apps & assistants |
| 4490 | Active (pushed in the last 90 days)perplexityai/numbat Visibility into AI agent activity on endpoints, with on-device detection, optional pre-action blocking, and forensic reconstruction. 1.2K—Go Agent frameworks |
| 4491 | Slowing down (last push 3–12 months ago)HacxGPT-Official/HacxGPT-CLI Open-source CLI for unrestricted AI - Access powerful models without censorship 1.2K—Python Chat apps & assistants |
| 4492 | Active (pushed in the last 90 days)lhotse-speech/lhotse Tools for handling multimodal data in machine learning projects. 1.2K—Python Training & fine-tuning |
| 4493 | Active (pushed in the last 90 days)okou-ai/okou Okou connects to the tools your team already uses and does the work — across marketing, sales, engineering, and operations, under your control. 1.2K—TypeScript Agent frameworks |
| 4494 | Inactive (no push for over a year, or archived)ricklamers/shell-ai LangChain powered shell command generator and runner CLI 1.2K—Python LLM & foundation models |
| 4495 | Slowing down (last push 3–12 months ago)character-ai/prompt-poet Streamlines and simplifies prompt design for both developers and non-technical users with a low code approach. 1.2K—Python LLM & foundation models |
| 4496 | Slowing down (last push 3–12 months ago)chengtan9907/OpenSTLDocs OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning 1.2K—Python Training & fine-tuning |
| 4497 | Slowing down (last push 3–12 months ago)noahcao/OC_SORT [CVPR2023] The official repo for OC-SORT: Observation-Centric SORT on video Multi-Object Tracking. OC-SORT is simple, online and robust to occlusion/non-linear motion. 1.2K—Python Computer vision |
| 4498 | Active (pushed in the last 90 days)hexabot-ai/Hexabot Hexabot v3 is an AI workflow automation platform, combining workflows, actions, agents, and conversational channels in one runtime. 1.2K—TypeScript LLM & foundation models |
| 4499 | Active (pushed in the last 90 days)aiptimizer/TurboOCR TurboOCR, >200 img/s OmnidocBench. TensorRT FP16, PP-OCRv6, HTTP + gRPC 1.2K—C++ Computer vision |
| 4500 | Active (pushed in the last 90 days)mgonzs13/yolo_ros Ultralytics YOLOv8, YOLOv9, YOLOv10, YOLOv11, YOLOv12 for ROS 2 1.2K—C++ Computer vision |