Trending reposUpdated daily from GitHub
Curated GitHub repos: standout and rising.
Curated GitHub repos: standout and rising.
| # | Repo |
|---|---|
| 4851 | Inactive (no push for over a year, or archived)yashbhalgat/HashNeRF-pytorch Pure PyTorch Implementation of NVIDIA paper on Instant Training of Neural Graphics primitives: https://nvlabs.github.io/instant-ngp/ 1K—Python Computer vision |
| 4852 | Active (pushed in the last 90 days)bilibili/Index-1.9B A lightweight multilingual LLM 1K—Python LLM & foundation models |
| 4853 | Inactive (no push for over a year, or archived)TorchEnsemble-Community/Ensemble-Pytorch A unified ensemble framework for PyTorch to improve the performance and robustness of your deep learning model. 1K—Python Training & fine-tuning |
| 4854 | Active (pushed in the last 90 days)open-mercato/cezar Open-source orchestrator and ADE for running Claude Code, Codex, OpenCode, Pi and other AI coding agents in parallel — locally or 24/7 on your own server. 1K—TypeScript Agent frameworks |
| 4855 | Active (pushed in the last 90 days)vastxie/99AI 开源、可私有化部署的 Web Agent 底座，支持多用户、隔离沙箱，以及 Skills 和 MCP 扩展。Open-source, self-hostable Web Agent foundation with multi-user support, isolated sandboxes, and extensibility through Skills and MCP. 1K—TypeScript Chat apps & assistants |
| 4856 | Active (pushed in the last 90 days)benchflow-ai/awesome-evalsDocs A curated, non-BS library of the best resources for building and evaluating AI agents — papers, blogs, talks, tools, benchmarks. Maintained by BenchFlow. 1K— LLMOps & evaluation |
| 4857 | Inactive (no push for over a year, or archived)keijiro/Pix2Pix Real-time pix2pix implementation with Unity 1K—C# Training & fine-tuning |
| 4858 | Slowing down (last push 3–12 months ago)gigwegbe/tinyml-papers-and-projects This is a list of interesting papers and projects about TinyML. 1K— Computer vision |
| 4859 | Active (pushed in the last 90 days)FalkorDB/GraphRAG-SDK Build fast and accurate GenAI apps with GraphRAG SDK at scale 🌟 1K—Python LLM & foundation models |
| 4860 | Active (pushed in the last 90 days)beizhu-1209/AIHelms 企业级 AI 资源纳管平台，提供统一 AI网关、Token调度能力，纳管 OpenAI、Azure、Claude、DeepSeek 等主流模型，并支持 MCP 工具与 Skill 的集中注册分发。具备内外双轨定价、成本归因、统一身份认证、安全审计与效能报表，帮助企业精准控制成本、量化 ROI，高效治理 AI 资产。 1K—Python Chat apps & assistants |
| 4861 | Inactive (no push for over a year, or archived)towardsai/tutorialsDocs AI-related tutorials. Access any of them for free → https://towardsai.net/editorial 1K—Jupyter Notebook Training & fine-tuning |
| 4862 | Inactive (no push for over a year, or archived)qubvel/ttach Image Test Time Augmentation with PyTorch! 1K—Python Training & fine-tuning |
| 4863 | Inactive (no push for over a year, or archived)aws-samples/aws-machine-learning-university-accelerated-tab Machine Learning University: Accelerated Tabular Data Class 1K—Jupyter Notebook Training & fine-tuning |
| 4864 | |
| 4865 | Inactive (no push for over a year, or archived)pinecone-io/canopy(archived) Retrieval Augmented Generation (RAG) framework and context engine powered by Pinecone 1K—Python RAG, memory & search |
| 4866 | Inactive (no push for over a year, or archived)sicara/tf-explain Interpretability Methods for tf.keras models with Tensorflow 2.x 1K—Python Training & fine-tuning |
| 4867 | Inactive (no push for over a year, or archived)GANs-in-Action/gans-in-action Companion repository to GANs in Action: Deep learning with Generative Adversarial Networks 1K—Jupyter Notebook Training & fine-tuning |
| 4868 | Slowing down (last push 3–12 months ago)Minqi824/ADBench Official Implement of "ADBench: Anomaly Detection Benchmark", NeurIPS 2022. 1K—Python Training & fine-tuning |
| 4869 | Inactive (no push for over a year, or archived)ZhiqingXiao/rl-book Source codes for the book "Reinforcement Learning: Theory and Python Implementation" 1K—HTML Training & fine-tuning |
| 4870 | Active (pushed in the last 90 days)microsoft/XStudio Intelligent cloud testing made easy. 1K—Java Chat apps & assistants |
| 4871 | Inactive (no push for over a year, or archived)Jumpat/SegmentAnythingin3D Segment Anything in 3D with NeRFs (NeurIPS 2023 & IJCV 2025) 1K—Python Training & fine-tuning |
| 4872 | Active (pushed in the last 90 days)taishi-i/awesome-japanese-nlp-resourcesDocs A curated list of resources for Japanese natural language processing (NLP): Python libraries, LLMs, dictionaries, corpora, and datasets. Includes Claude Code and Codex skills to search resources. 1K— LLM & foundation models |
| 4873 | Slowing down (last push 3–12 months ago)ClementPinard/SfmLearner-Pytorch Pytorch version of SfmLearner from Tinghui Zhou et al. 1K—Python Training & fine-tuning |
| 4874 | Active (pushed in the last 90 days)opencrabs/opencrabs The all-in-one AI agent. Build mobile apps, frontend, backend, manages files, deep research, schedule tasks and events. Self-improving, self-healing, fully autonomous. TUI, CLI and Daemon. Connect to your favorite channels. Zero Telemetry. 1K—Rust Agent frameworks |
| 4875 | Active (pushed in the last 90 days)ConardLi/easy-agent Production-ready open source terminal coding agent with readable, layered code: permission rules, OS sandboxing, MCP, skills, sub-agents, and Anthropic, OpenAI-compatible, Gemini, or local models. 1K—TypeScript Chat apps & assistants |
| 4876 | Active (pushed in the last 90 days)simplexai-labs/PolyStrata Run large AI models on your own PC: Qwen3.8-Flash-Next on Strata's engine, and GLM 5.3 Flash, DeepSeek V4 Flash, LFM2.5, Qwen3.6, Ornith 1.5, Gemma 4, Tiel Coder and MiniCPM-V on a second engine written for PolyStrata. One-click install for Windows and Linux, OpenAI/Anthropic API on localhost. 1K—C++ LLM & foundation models |
| 4877 | Active (pushed in the last 90 days)yukkcat/chatgpt2api ChatGPT官网接口纯协议的逆向实现，支持注册机维持号池额度，支持GPT-Image-2模型、文本模型，兼容OpenAI接口协议，在线批量生图/编辑图，号池管理，支持可编辑PPT/PSD文件逆向，支持导入CPA、sub2api号池 、支持接入Cherry Studio、New Api 等软件 1K—Python Chat apps & assistants |
| 4878 | Active (pushed in the last 90 days)microsoft/Tutel Tutel MoE: Optimized Mixture-of-Experts Library, Support GLM/Kimi/Gpt/DeepSeek/Qwen using FP8/NVFP4/MXFP4 1K—C LLM & foundation models |
| 4879 | Slowing down (last push 3–12 months ago)ethz-spylab/agentdojo A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents. 1K—Python LLM & foundation models |
| 4880 | Slowing down (last push 3–12 months ago)shanraisshan/codex-cli-best-practice from vibe coding to agentic engineering - practice makes codex perfect 1K—Python Agent frameworks |
| 4881 | Slowing down (last push 3–12 months ago)thuml/Large-Time-Series-Model Official code, datasets and checkpoints for "Timer: Generative Pre-trained Transformers Are Large Time Series Models" (ICML 2024) and subsequent works 1K—Python LLM & foundation models |
| 4882 | Active (pushed in the last 90 days)urzeye/ophel Turn AI conversations into organized, reusable workflows — across major AI platforms. | 把 AI 对话转化为可组织、可复用的工作流，适用于主流 AI 平台 1K—TypeScript Chat apps & assistants |
| 4883 | Inactive (no push for over a year, or archived)unrealcv/synthetic-computer-vision A list of synthetic dataset and tools for computer vision 1K—Python Computer vision |
| 4884 | Active (pushed in the last 90 days)abahmed/kwatch kwatch runs inside your Kubernetes cluster, traces every failure to its root cause, and sends one message: what broke, why, who changed it and what to do next. 1K—Go LLMOps & evaluation |
| 4885 | Inactive (no push for over a year, or archived)KevinGong2013/ChineseIDCardOCR [Deprecated] 🇨🇳中国二代身份证光学识别 1K—Swift Training & fine-tuning |
| 4886 | Active (pushed in the last 90 days)Zyrexnn/Cybermes Autonomous Offensive Security, Bug Bounty & Red Teaming Agent Framework powered by Hermes Agent, specialized reasoning skills, and multi-model LLM orchestration. 1K—Python Agent frameworks |
| 4887 | Inactive (no push for over a year, or archived)openai/openai-realtime-api-beta Node.js + JavaScript reference client for the Realtime API (beta) 1K—JavaScript Chat apps & assistants |
| 4888 | Inactive (no push for over a year, or archived)awslabs/multi-model-server(archived) Multi Model Server is a tool for serving neural net models for inference 1K—Java Inference & local LLM |
| 4889 | Active (pushed in the last 90 days)yueliu1999/Awesome-Deep-Graph-ClusteringDocs [IEEE T-KDE 2026] Awesome Deep Graph Clustering is a collection of SOTA, novel deep graph clustering methods (papers, codes, and datasets). 1K—Python Training & fine-tuning |
| 4890 | Slowing down (last push 3–12 months ago)FareedKhan-dev/production-grade-agentic-system Core 7 layers of production grade agentic system 1K—Python Agent frameworks |
| 4891 | Active (pushed in the last 90 days)kennss/SiliconScope Sudoless Apple Silicon system monitor (native SwiftUI GUI) with ANE / Media Engine / memory-bandwidth tracking 1K—Swift Inference & local LLM |
| 4892 | Slowing down (last push 3–12 months ago)tapparelj/gr-lora_sdr This is the fully-functional GNU Radio software-defined radio (SDR) implementation of a LoRa transceiver with all the necessary receiver components to operate correctly even at very low SNRs. This work has been conducted at the Telecommunication Circuits Laboratory, EPFL. 1K—C++ Training & fine-tuning |
| 4893 | Inactive (no push for over a year, or archived)jucasoliveira/terminalGPT Get GPT like chatGPT on your terminal 1K—TypeScript Chat apps & assistants |
| 4894 | Active (pushed in the last 90 days)RupertAvery/DiffusionToolkit Metadata-indexer and Viewer for AI-generated images 1K—C# Image generation |
| 4895 | Inactive (no push for over a year, or archived)zabirauf/AutoGPT.js Auto-GPT on the browser 1K—TypeScript LLM & foundation models |
| 4896 | Active (pushed in the last 90 days)sophgo/tpu-mlir Machine learning compiler based on MLIR for Sophgo TPU. 1K—C++ LLM & foundation models |
| 4897 | Inactive (no push for over a year, or archived)sniklaus/sepconv-slomo an implementation of Video Frame Interpolation via Adaptive Separable Convolution using PyTorch 1K—Python Training & fine-tuning |
| 4898 | Inactive (no push for over a year, or archived)natowi/3D-Reconstruction-with-Deep-Learning-Methods List of projects for 3d reconstruction 1K— Training & fine-tuning |
| 4899 | Inactive (no push for over a year, or archived)maximeraafat/BlenderNeRF Easy NeRF synthetic dataset creation within Blender 1K—Python Computer vision |
| 4900 | Inactive (no push for over a year, or archived)dillionverma/llm.report(archived) 📊 llm.report is an open-source logging and analytics platform for OpenAI: Log your ChatGPT API requests, analyze costs, and improve your prompts. 1K—TypeScript LLM & foundation models |