DeepLearningDTU/02456-2026: Repository for the DTU deep learning course (02456) in the fall of 2026
Repository for the DTU deep learning course (02456) in the fall of 2026
Repositories
baidu-baige/LoongSage: A production-grade, high-efficiency Agentic RL framework for frontier LLMs with validated recipes.
A production-grade, high-efficiency Agentic RL framework for frontier LLMs with validated recipes.
carloslfu/slotstream: Run Qwen3.8-Flash-Next (125B MoE, 104 GB at 4-bit) on Macs with a fraction of that RAM by streaming experts from SSD. MLX + Swift, Ollama-compatible API.
Run Qwen3.8-Flash-Next (125B MoE, 104 GB at 4-bit) on Macs with a fraction of that RAM by streaming experts from SSD. MLX + Swift, Ollama-compatible API.
divanshusingh-ds/pandavision: Touchless Panda Runner - Play with your body movements using webcam!
Touchless Panda Runner - Play with your body movements using webcam!
Nanako0129/sepia: De-AI writing skill for Claude Code, Codex, Grok Build, and Antigravity — narrative-architecture repair for fiction, venue-matched rules for professional prose. Based on StoryScope (arXiv:2604.03136).
De-AI writing skill for Claude Code, Codex, Grok Build, and Antigravity — narrative-architecture repair for fiction, venue-matched rules for professional prose. Based on StoryScope...
abidsgx/Machine-Learning-Model-for-Stock-Market: Machine learning models designed for stock market price prediction from analyzing time series data. Includes backtesting script to visualise the model's performance.
Machine learning models designed for stock market price prediction from analyzing time series data. Includes backtesting script to visualise the model's performance.
ZJU-REAL/Easel: An open-source AI agent for social media — discover trends, create content, publish everywhere, and learn what works across Xiaohongshu, Douyin, Zhihu, Bilibili, and more.
An open-source AI agent for social media — discover trends, create content, publish everywhere, and learn what works across Xiaohongshu, Douyin, Zhihu, Bilibili, and more.
brayonpi/hexstellar: Turn any AI agent into a computational researcher. HexStellar Cortex delivers software-accelerated optimization, quantum computing, scientific computing, decision intelligence, and verifiable execution through a Python CLI and API—with certainty labels, verification receipts, examples, and a free sandbox. Start instantly: pip install hexstellar
Turn any AI agent into a computational researcher. HexStellar Cortex delivers software-accelerated optimization, quantum computing, scientific computing, decision intelligence, and...
Nystic-Shadow/reve-openai-proxy: ⚡ High-Performance OpenAI-Compatible Image Generation API Proxy for Reve.com with Native 4K Ultra-HD Diffusion & Multi-Account Load Balancing
⚡ High-Performance OpenAI-Compatible Image Generation API Proxy for Reve.com with Native 4K Ultra-HD Diffusion & Multi-Account Load Balancing
mem-audit/memaudit: Training-data memorization auditor for fine-tuned LLMs — Trainer/TRL plugin, canary MIA + regurgitation audit, Apache-2.0
Training-data memorization auditor for fine-tuned LLMs — Trainer/TRL plugin, canary MIA + regurgitation audit, Apache-2.0
OnlyTerp/opengrok: Run any model in Grok Bot — one-command setup, model picker UI, evidence-based provider wire maps, and an update-proof doctor. Not farming you, arming you.
Run any model in Grok Bot — one-command setup, model picker UI, evidence-based provider wire maps, and an update-proof doctor. Not farming you, arming you.
loonylabs-dev/strix-halo-inference: Measured inference stack for Strix Halo (Ryzen AI Max+ 395, 128 GB) — llama.cpp serving plus TTS/TTI/TTV media workloads under one memory authority. Not a fork: master plus a short list of patches. Memory budget, defect registry, prefix-cache gateway.
Measured inference stack for Strix Halo (Ryzen AI Max+ 395, 128 GB) — llama.cpp serving plus TTS/TTI/TTV media workloads under one memory authority. Not a fork: master plus a short...
bearded-impala/generative-ai-history-presentation: A cinematic 3D presentation tracing the history of generative AI from Turing to transformers and modern scaling laws.
A cinematic 3D presentation tracing the history of generative AI from Turing to transformers and modern scaling laws.
hkqr/my-free-code: Open-source multi-provider AI gateway for Claude Code and other coding agents, with model routing, streaming, tools, reasoning, fallbacks, and local model support
Open-source multi-provider AI gateway for Claude Code and other coding agents, with model routing, streaming, tools, reasoning, fallbacks, and local model support
WeizhiZhang051029/MTAM-HG-A-Mixture-of-Experts-Heterogeneous-Graph-Network-with-Agent-Regulated-Diffusion-Augmentation: MTAM-HG-A Mixture-of-Experts Heterogeneous Graph Network with Agent-Regulated Diffusion Augmentation
MTAM-HG-A Mixture-of-Experts Heterogeneous Graph Network with Agent-Regulated Diffusion Augmentation
Sakshamxx/Ortho-Sense-AI: OrthoSense is an AI-powered healthcare solution that uses CNNs and machine learning to analyze orthopedic conditions, assist with early detection, and provide intelligent, data-driven insights through an easy-to-use interface.
OrthoSense is an AI-powered healthcare solution that uses CNNs and machine learning to analyze orthopedic conditions, assist with early detection, and provide intelligent, data-dri...
damejan80/tokentab: A CLI that reads Claude Code, Codex, and Gemini CLI session logs and works out how much they cost, by model, project, and day.
A CLI that reads Claude Code, Codex, and Gemini CLI session logs and works out how much they cost, by model, project, and day.
grownvogue/Stable-Diffusion-Crack: Free download Stable Diffusion Crack for Windows — full version activated, all features unlocked. Working 2026.
Free download Stable Diffusion Crack for Windows — full version activated, all features unlocked. Working 2026.
JordyZomer/lemmalog: A Datalog engine for LLM agent memory: stratified rules, provenance-tracked facts, incremental derivation, and an MCP server that lets your harness use it as a shared brain.
A Datalog engine for LLM agent memory: stratified rules, provenance-tracked facts, incremental derivation, and an MCP server that lets your harness use it as a shared brain.
leopard627/fire-your-seo-agency: Fire your SEO·GEO agency 🔥 A Claude Code skill that audits and optimizes SEO·AEO·GEO·LLMO·NEO(Naver) by itself — 월 50~350만 원짜리 'AI 검색 최적화' 대행, AI 에이전트가 대체합니다
Fire your SEO·GEO agency 🔥 A Claude Code skill that audits and optimizes SEO·AEO·GEO·LLMO·NEO(Naver) by itself — 월 50~350만 원짜리 'AI 검색 최적화' 대행, AI 에이전트가 대체합니다
grayshoat/Firefly-Desktop---Adobe-Firefly-AI-2026: Firefly-Desktop - Adobe Firefly AI with text-to-image, generative fill, and text effects.
Firefly-Desktop - Adobe Firefly AI with text-to-image, generative fill, and text effects.
achingconvect/SD-Desktop---Stable-Diffusion-Desktop-2026: SD-Desktop - one-click Stable Diffusion installer with auto-configured CUDA and model manager.
SD-Desktop - one-click Stable Diffusion installer with auto-configured CUDA and model manager.
amusedboot/MJ-Desktop---Midjourney-AI-Desktop-App-2026: MJ-Desktop - Midjourney AI image generator for Windows with offline mode and batch processing.
MJ-Desktop - Midjourney AI image generator for Windows with offline mode and batch processing.
PAICNI/CFBox: 一个运行在 Cloudflare Workers 上兼容CFnew 与edgetunnel的代理订阅管理面板——既能在 /UUID 路径上输出 VLESS/Trojan/xhttp 多协议订阅，又提供图形化配置界面（KV 存储、改完即生效），并内置延迟测试、流媒体/AI 连通性检测、多客户端订阅生成、多语言等能力。
一个运行在 Cloudflare Workers 上兼容CFnew 与edgetunnel的代理订阅管理面板——既能在 /UUID 路径上输出 VLESS/Trojan/xhttp 多协议订阅，又提供图形化配置界面（KV 存储、改完即生效），并内置延迟测试、流媒体/AI 连通性检测、多客户端订阅生成、多语言等能力。