Trending reposUpdated daily from GitHub
Curated GitHub repos: standout and rising.
Curated GitHub repos: standout and rising.
| # | Repo |
|---|---|
| 5751 | Inactive (no push for over a year, or archived)abhimishra91/transformers-tutorials Github repo with tutorials to fine tune transformers for diff NLP tasks 863—Jupyter Notebook Training & fine-tuning |
| 5752 | Inactive (no push for over a year, or archived)iMoonLab/HGNN Hypergraph Neural Networks (AAAI 2019) 863—Python Training & fine-tuning |
| 5753 | Inactive (no push for over a year, or archived)radekd91/emoca Official repository accompanying a CVPR 2022 paper EMOCA: Emotion Driven Monocular Face Capture And Animation. EMOCA takes a single image of a face as input and produces a 3D reconstruction. EMOCA sets the new standard on reconstructing highly emotional images in-the-wild 863—Python Training & fine-tuning |
| 5754 | Inactive (no push for over a year, or archived)safe-graph/graph-adversarial-learning-literatureDocs A curated list of adversarial attacks and defenses papers on graph-structured data. 863— Training & fine-tuning |
| 5755 | Active (pushed in the last 90 days)Pangu-Immortal/MagicWX Android 17 local LLM prototype with Jetpack Compose and ONNX Runtime for offline AI inference experiments. 863—Kotlin Inference & local LLM |
| 5756 | Active (pushed in the last 90 days)sherwinvishesh/SurrogateShield A privacy-first guardrail for LLMs and RAG pipelines. SurrogateShield detects, redacts, and reconstructs sensitive PII data on the fly while defending against adversarial attacks. 863—Python Chat apps & assistants |
| 5757 | Active (pushed in the last 90 days)genex-games/genex-desktop Desktop app for game dev with AI: make games in Unreal Engine, Unity, Godot or the browser. The agent sets up the engine, builds your game and play-tests it by itself. 863—TypeScript Coding agents & assistants |
| 5758 | Active (pushed in the last 90 days)hank-ai/darknet Darknet/YOLO object detection framework 862—C++ Computer vision |
| 5759 | Inactive (no push for over a year, or archived)lucidrains/meshgpt-pytorch Implementation of MeshGPT, SOTA Mesh generation using Attention, in Pytorch 862—Python Training & fine-tuning |
| 5760 | Inactive (no push for over a year, or archived)berniwal/swin-transformer-pytorch Implementation of the Swin Transformer in PyTorch. 862—Python Training & fine-tuning |
| 5761 | Inactive (no push for over a year, or archived)cfzd/Ultra-Fast-Lane-Detection-v2 Ultra Fast Deep Lane Detection With Hybrid Anchor Driven Ordinal Classification (TPAMI 2022) 862—Python Training & fine-tuning |
| 5762 | Inactive (no push for over a year, or archived)langgptai/LLM-Jailbreaks LLM Jailbreaks, ChatGPT, Claude, Llama, DAN Prompts, Prompt Leaking 862— Chat apps & assistants |
| 5763 | Active (pushed in the last 90 days)rahilp/second-brain-cloudflare One memory layer, every AI tool. Store anything once — recall it in Claude, ChatGPT, Cursor, or any MCP client. Self-hosted on Cloudflare's free tier. 862—TypeScript MCP servers & tools |
| 5764 | Slowing down (last push 3–12 months ago)zhaoxinyi02/ClawPanel 🐾 ClawPanel — OpenClaw AI 助手可视化管理面板。Go 单二进制部署，支持 20+ 通道统一管理，跨平台，实时日志监控。 861—Go Chat apps & assistants |
| 5765 | Inactive (no push for over a year, or archived)jia-zhuang/pytorch-multi-gpu-training 整理 pytorch 单机多 GPU 训练方法与原理 861—Python Training & fine-tuning |
| 5766 | Inactive (no push for over a year, or archived)gmalivenko/pytorch2keras PyTorch to Keras model convertor 861—Python Training & fine-tuning |
| 5767 | Active (pushed in the last 90 days)juggler-ai/juggler The Juggler Code Agent 861—JavaScript Agent frameworks |
| 5768 | Inactive (no push for over a year, or archived)shibing624/ChatPDF RAG for Local LLM, chat with PDF/doc/txt files, ChatPDF. 纯原生实现RAG功能，基于本地LLM、embedding模型、reranker模型实现，支持GraphRAG，无须安装任何第三方agent库。 861—Python RAG, memory & search |
| 5769 | Active (pushed in the last 90 days)niieani/gpt-tokenizer The fastest JavaScript BPE Tokenizer Encoder Decoder for OpenAI's GPT models (gpt-5, gpt-o*, gpt-4o, etc.). Port of OpenAI's tiktoken with additional features. 860—TypeScript Chat apps & assistants |
| 5770 | Active (pushed in the last 90 days)Regncreative/PulseDiagnostics Read-only Windows diagnostics: the Event Log in plain language, blue screens explained. Offline and open source. 860—Dart LLMOps & evaluation |
| 5771 | Slowing down (last push 3–12 months ago)kymatio/kymatio Wavelet scattering transforms in Python with GPU acceleration 860—Python Training & fine-tuning |
| 5772 | Active (pushed in the last 90 days)whitecircle/halo Halo is an open-source framework built by White Circle for training large language and multimodal models 860—Python Training & fine-tuning |
| 5773 | Inactive (no push for over a year, or archived)parlance/ctcdecode PyTorch CTC Decoder bindings 859—C++ Training & fine-tuning |
| 5774 | Inactive (no push for over a year, or archived)bupt-ai-cz/LLVIP LLVIP: A Visible-infrared Paired Dataset for Low-light Vision 859—Jupyter Notebook Computer vision |
| 5775 | Inactive (no push for over a year, or archived)jeya-maria-jose/Medical-Transformer Official Pytorch Code for "Medical Transformer: Gated Axial-Attention for Medical Image Segmentation" - MICCAI 2021 859—Python Training & fine-tuning |
| 5776 | Active (pushed in the last 90 days)gavamedia/deltafin Run full Kimi K3 on a single device. And an OpenAI-compatible API server for local chat and coding agents. 859—Rust Inference & local LLM |
| 5777 | Inactive (no push for over a year, or archived)pengsongyou/openscene [CVPR'23] OpenScene: 3D Scene Understanding with Open Vocabularies 859—Python LLM & foundation models |
| 5778 | Inactive (no push for over a year, or archived)google/generative-ai-go(archived) Go SDK for Google Generative AI 859—Go LLM & foundation models |
| 5779 | Active (pushed in the last 90 days)huangjia2019/rag-in-action End-to-end RAG system design, evaluation, and optimization. 极客时间RAG训练营，RAG 10大组件全面拆解，4个实操项目吃透 RAG 全流程。RAG的落地，往往是面向业务做RAG，而不是反过来面向RAG做业务。这就是为什么我们需要针对不同场景、不同问题做针对性的调整、优化和定制化。魔鬼全在细节中，我们深入进去探究。 859—Jupyter Notebook RAG, memory & search |
| 5780 | Inactive (no push for over a year, or archived)wasidennis/AdaptSegNet Learning to Adapt Structured Output Space for Semantic Segmentation, CVPR 2018 (spotlight) 858—Python Training & fine-tuning |
| 5781 | Active (pushed in the last 90 days)netease-youdao/Confucius4-TTS Confucius4-TTS: a Multilingual and Cross-Lingual Zero-Shot TTS Engine 858—Python Text-to-speech (TTS) |
| 5782 | Slowing down (last push 3–12 months ago)WooooDyy/AgentGym Code and implementations for the ACL 2025 paper "AgentGym: Evolving Large Language Model-based Agents across Diverse Environments" by Zhiheng Xi et al. 858—Python LLM & foundation models |
| 5783 | Inactive (no push for over a year, or archived)ReceiptManager/receipt-parser-legacy A supermarket receipt parser written in Python using tesseract OCR 857—Python Computer vision |
| 5784 | Inactive (no push for over a year, or archived)chain-ml/council Council is an open-source platform for the rapid development and robust deployment of customized generative AI applications 857—Python Chat apps & assistants |
| 5785 | Inactive (no push for over a year, or archived)HazyResearch/meerkat Explore and understand your training and validation data. 857—Python LLM & foundation models |
| 5786 | Active (pushed in the last 90 days)hoophq/hoop Open-source enforcement at runtime that masks sensitive data and blocks destructive commands from AI agents. You change one thing: your agent's port. 857—Go LLM & foundation models |
| 5787 | Inactive (no push for over a year, or archived)Atome-FE/llama-node(archived) Believe in AI democratization. llama for nodejs backed by llama-rs, llama.cpp and rwkv.cpp, work locally on your laptop CPU. support llama/alpaca/gpt4all/vicuna/rwkv model. 857—Rust LLM & foundation models |
| 5788 | Active (pushed in the last 90 days)IncarnaMind/IncarnaMind From messy files to a checked report. A free, open-source desktop app for macOS, Windows and Linux: write and analyse with AI from your own files, check each sentence and figure against them, and export to Word. Meeting notes too. Works with ChatGPT, Claude, Gemini or a local model through Ollama. 857—TypeScript Inference & local LLM |
| 5789 | Inactive (no push for over a year, or archived)brade31919/SRGAN-tensorflow Tensorflow implementation of the SRGAN algorithm for single image super-resolution 856—Python Training & fine-tuning |
| 5790 | Inactive (no push for over a year, or archived)pchunduri6/rag-demystified An LLM-powered advanced RAG pipeline built from scratch 856—Python RAG, memory & search |
| 5791 | Active (pushed in the last 90 days)YeonwooSung/llm-architecture-from-scratch Implementing LLM architectures from scratch in PyTorch 856—Python LLM & foundation models |
| 5792 | Active (pushed in the last 90 days)NickSwardh/YoloDotNet YoloDotNet - A C# .NET 8.0 project for Classification, Object Detection, OBB Detection, Segmentation and Pose Estimation in both images and live video streams. 856—C# Computer vision |
| 5793 | Inactive (no push for over a year, or archived)pipeless-ai/pipeless An open-source computer vision framework to build and deploy apps in minutes 856—Rust Computer vision |
| 5794 | Active (pushed in the last 90 days)zexadev/gemini-web2api-go Gemini web → OpenAI-compatible + native Gemini API, self-hosted, no API key. Gemini 4 Argon from a paid account cookie, strict_model (429 instead of a silent downgrade), cookie pool with auto-renewal, proxy pool, admin panel, image & video generation, single Go binary · 把 Gemini 网页反代成 OpenAI 兼容 / Gemini 原生 API，付费号 cookie 直接用 4 Argon 855—Go Chat apps & assistants |
| 5795 | Inactive (no push for over a year, or archived)dissorial/doc-chatbot Document chatbot — multiple files, topics, chat windows and chat history. Powered by GPT. 855—TypeScript Chat apps & assistants |
| 5796 | Inactive (no push for over a year, or archived)ProGamerGov/neural-style-pt PyTorch implementation of neural style transfer algorithm 855—Python Training & fine-tuning |
| 5797 | Inactive (no push for over a year, or archived)Zhen-Dong/Awesome-Quantization-PapersDocs List of papers related to neural network quantization in recent AI conferences and journals. 855— Inference & local LLM |
| 5798 | Inactive (no push for over a year, or archived)Oneirocom/Magick Magick is a cutting-edge toolkit for a new kind of AI builder. Make Magick with us! 855—TypeScript LLM & foundation models |
| 5799 | Slowing down (last push 3–12 months ago)waylaidwanderer/PandoraAI PandoraAI is a web chat client powered by node-chatgpt-api, allowing users to easily chat with multiple AI systems while also offering support for custom presets. With its seamless and convenient design, PandoraAI provides an engaging conversational AI experience. 854—Vue Chat apps & assistants |
| 5800 | Inactive (no push for over a year, or archived)26hzhang/DL-NLP-Readings My Reading Lists of Deep Learning and Natural Language Processing 854—TeX Training & fine-tuning |