Stars
- All languages
- Assembly
- Batchfile
- C
- C#
- C++
- CSS
- Clojure
- Cuda
- Cycript
- Dart
- Dockerfile
- Elixir
- Go
- HTML
- Haskell
- Java
- JavaScript
- Julia
- Jupyter Notebook
- Kotlin
- LLVM
- Lua
- MATLAB
- MDX
- Makefile
- Markdown
- Meson
- Objective-C
- Objective-C++
- PHP
- PLSQL
- Pascal
- Perl
- PostScript
- PowerShell
- PureBasic
- Python
- Roff
- Ruby
- Rust
- SCSS
- Sass
- Scala
- Shell
- Smarty
- Solidity
- SourcePawn
- Swift
- TSQL
- TeX
- TypeScript
- Visual Basic .NET
- Vue
- YARA
Editorial diagram design for Claude Code, Codex, GitHub Copilot, Cursor, Factory Droid, Qoder, and Pi. 45 diagram types. Self-contained HTML + SVG. No shadows. No Mermaid slop.
Qwen3.8-Flash-Next (125B MoE) up to 1M context on one or two RTX cards (tuned on 3080 10gb). A measured, tuned and benchmarked fork of Strata.
Claude 官方最佳实践全集:173 篇中文译文 + 100 个概念的 LLM Wiki 知识网 + 交互式知识图谱/思维导图
Proof-of-concept (PoC) scripts for CVE-2026-123007, an integer underflow in NGINX HTTP/2.
🧠 两小时从 0 训出你的 64M 大模型。Train your own 64M LLM from scratch in 2 hours.
A 25.7M-parameter GLM-5.3-Flash-inspired model trained from scratch and improved with executable-reward RL.
A free course in ten notebooks: an English–Russian translator written in PyTorch from the tokenizer up, trained on a free GPU, evaluated and shipped as a Docker image
给国产电视的一块干净桌面:参照 tvOS 设计的开源 Android TV 桌面,没有广告,开机自动接管。A tvOS-style launcher for Xiaomi, TCL and other China-market TVs.
A translation-based Apple Silicon layer for x86-64 PCs
Poki uses your iPhone like you do. An open-source agent app that runs on your iPhone, reads the screen, and taps, types and swipes in real apps with your own model account.
small LLM inference engine from scratch, w/ 6+ hours of youtube tutorials & 85+ pages of handwritten notes included
An MobileGestalt editor for iOS 27.x, featuring region-code tweaks, device presets, backups.
Blender's GPU Accelerated UI, Decoupled from it's original codebase. Supports Rust, Python, JS, Lua, C & C++. Twice as good as GPUI
OBLITERATE THE CHAINS THAT BIND YOU
Zero-GPU CPU inference for 30B-284B MoE models (Qwen3.8 176.5B cold-cache certified in 28.26/48.35 GiB Cgroup v2, DeepSeek-V4 284B, Nemotron-30B) + RouteCrack 2.0.
Let AI use your iPhone or Android phone, with you in the loop: any MCP agent from macOS, Windows or Linux, or Pinky itself, right on the phone.
llama.cpp fork for significantly improved performance on Ampere generation Nvidia cards (especially RTX 3090 / 3090 Ti): example: 110+ tok/s over a 100K-token generation at temperature 1 for qwen3.…
Craft Anything: understand how any software works, and craft your own.
Unlocking _everything_ on the CPU with DRAM scrambling
基于内核漏洞CVE-2026-43499的本地提权适配,集成嵌入式 KernelSU.CVE-2026-43499+KernelSU越狱模式
🐋 大肥鱼 · AstrBot QQ 机器人全家桶:会看会听会说话、有记忆、会主动找你的鲸鱼娘(AstrBot + NapCat + DeepSeek + 阿里云百炼)
A Unified Framework for Efficient RSI Research
Practice English, one strike, one step forward
roothide / Dopamine-roothide
Forked from opa334/DopamineOpen-source integration of roothide and Dopamine 3.x
🛡️ BLA (bla-agents / Blind LLM Agents) — Open-source Blue Defense MCP server & CLI protecting JS/TS, Electron ASAR, WASM, Python, Native Binaries, SQLite, GGUF/Safetensors & Android DEX against AI …
Your GeForce runs AI at half speed. This fixes it for 20/30/40 series cards. Up to 2× FP16 / BF16 / TF32 tensor throughput
Capture iPhone LiDAR and photos, reconstruct editable Three.js rooms, and explore them in a browser.
The plugin market inside DeepSeek Harness — browse, search, one-click install · DSH 可视化插件市场
Work-in-progress static recompilation of The Legend of Zelda: Breath of the Wild (Switch, v1.9.0) for Windows and Linux. Bring your own dump: no game files, keys or dumping tools included.