The old advice to avoid Windows for local LLMs used to be right. It isn't anymore. The fixes for display-GPU desktop crashes and WSL memory limits, from people who run a 5090 daily.
GitHub repository with 12 stars and 1 forks.
Language: PowerShell
Topics: cuda, llamacpp, llm, local-llm, nvidia, ollama, rtx-5090, tdr, windows, wsl2
Trending score 0.62, activity score 0.03, stars gained +3, forks gained +0.
2026-06-05: 12 stars and 1 forks.
The old advice to avoid Windows for local LLMs used to be right. It isn't anymore. The fixes for display-GPU desktop crashes and WSL memory limits, from people who run a 5090 daily.
GitHub repository with 12 stars and 1 forks.
Trending score: 0.62; stars gained: +3; forks gained: +0.
Language: PowerShell
Topics: cuda, llamacpp, llm, local-llm, nvidia, ollama
Claude Desktop Chinese Patch (macOS & Windows)
GitHub repository with 1,986 stars and 127 forks.
Trending score: 2.24; stars gained: +213; forks gained: +7.
Language: PowerShell
Automate the setup and configuration of your Windows development environment.
GitHub repository with 446 stars and 40 forks.
Trending score: 1.84; stars gained: +84; forks gained: +6.
Language: PowerShell
此skills用于指导智能体在 Windows 上恢复 Codex Desktop 升级后失效的本地补丁和能力开关。（Computer Use，插件，fast mode等问题）支持每次使用前自动将skills更新到最新版。/These skills are designed to guide the agent in restoring local patches and feature toggles that have been disabled or invalidated following a Codex Desktop upgrade on Windows. Supports auto-updating translations.
GitHub repository with 273 stars and 32 forks.
Trending score: 1.46; stars gained: +32; forks gained: +4.
Language: PowerShell
A portable agent skill for sharpening research questions.
GitHub repository with 77 stars and 5 forks.
Trending score: 1.12; stars gained: +13; forks gained: +0.
Language: PowerShell
Topics: agent-skill, ai-agents, research-ideation, research-questions, scientific-method
科研绘图skill、论文绘图skill、图片转visio等可编辑格式，将生成图转化为论文可编辑图，便于作者调整绘图细节
GitHub repository with 48 stars and 2 forks.
Trending score: 1.08; stars gained: +12; forks gained: +0.
Language: PowerShell
Topics: codex, skills, visio, academic-figures, scientific-figures, editable-diagrams
CSS patch for Claude Desktop windows version to enable RTL (right-to-left) support for Hebrew and Arabic
GitHub repository with 71 stars and 11 forks.
Trending score: 0.98; stars gained: +9; forks gained: +2.
Language: PowerShell
Topics: arabic, claude, claude-desktop, hebrew, patch, rtl
A high-throughput and memory-efficient inference and serving engine for LLMs
GitHub repository with 82,008 stars and 17,694 forks.
Trending score: 3.75; stars gained: +79; forks gained: +46.
Language: Python
Topics: amd, blackwell, cuda, deepseek, deepseek-v3, gpt
:metal: TT-NN operator library, and TT-Metalium low level kernel programming model.
GitHub repository with 1,495 stars and 481 forks.
Trending score: 1.82; stars gained: +7; forks gained: +5.
Language: C++
Topics: accelerator, ai, cuda, deepseek, gpu, img-gen
Real-time 3D full-body reconstruction from a single camera, Multiperson BVH output, Pure C++ runtime, ONNX + ggml, 70-joint skeleton with hands.
GitHub repository with 475 stars and 62 forks.
Trending score: 1.78; stars gained: +2; forks gained: +1.
Language: C
Topics: 3d-human-pose, bvh, computer-vision, cpp, cuda, ggml
SGLang is a high-performance serving framework for large language models and multimodal models.
GitHub repository with 28,865 stars and 6,350 forks.
Trending score: 1.72; stars gained: -55; forks gained: +18.
Language: Python
Topics: attention, blackwell, cuda, deepseek, diffusion, glm
Use your NVIDIA GPU's VRAM as swap space on Linux. Built for laptops with soldered memory and no upgrade path. If you have an RTX card sitting there with 8GB of VRAM and you're getting swapped to SSD, this puts that VRAM to work
GitHub repository with 399 stars and 10 forks.
Trending score: 1.53; stars gained: +39; forks gained: +0.
Language: Shell
Topics: cuda, gpu, laptop, linux, memory, nbd
FlashInfer: Kernel Library for LLM Serving
GitHub repository with 5,752 stars and 1,026 forks.
Trending score: 1.16; stars gained: +15; forks gained: +8.
Language: Python
Topics: attention, cuda, distributed-inference, gpu, jit, large-large-models