- Beijing
- http://yongzhen.wang
- All languages
- ANTLR
- ASL
- Assembly
- Astro
- Batchfile
- BitBake
- Blade
- BlitzBasic
- C
- C#
- C++
- CMake
- CSS
- Classic ASP
- Clojure
- CodeQL
- CoffeeScript
- Cuda
- Dart
- Dockerfile
- Emacs Lisp
- Erlang
- Fluent
- FreeMarker
- GDScript
- Go
- Go Template
- Groovy
- HCL
- HTML
- Haskell
- JSON
- Java
- JavaScript
- Jinja
- Julia
- Jupyter Notebook
- Kotlin
- LLVM
- Lean
- Lua
- MATLAB
- MDX
- MLIR
- Makefile
- Markdown
- Meson
- Mojo
- OCaml
- Objective-C
- Odin
- PHP
- PLSQL
- PLpgSQL
- Pascal
- Perl
- PostScript
- PowerShell
- Python
- R
- Ragel
- Raku
- Roff
- Ruby
- Rust
- SAS
- SCSS
- SMT
- SWIG
- Sage
- Scala
- Scilab
- Shell
- Smarty
- Starlark
- Svelte
- Swift
- TSQL
- TeX
- Tree-sitter Query
- TypeScript
- V
- Vala
- Verilog
- Vim Script
- Visual Basic 6.0
- Vue
- WebAssembly
- XSLT
- YARA
- ZIL
- Zig
Starred repositories
Worktrunk is a CLI for Git worktree management, designed for parallel AI agent workflows
基于 Playwright 和AI实现的闲鱼多任务实时/定时监控与智能分析系统,配备了功能完善的后台管理UI。帮助用户从闲鱼海量商品中,找到心仪产品。
An open source design system that's fully customizable and agent ready
Every agent's model. One place. Codex on DeepSeek, Claude Code on Kimi, from the menu bar.
DeepSeek Harness 破甲:让所有模型都能破甲,不同模型可换不同提示词;默认提示词面向国模「小码酱」。Jailbreak for every model — swap prompts per model. 求 Star 收藏 ⭐ 如要二开,请查看署名要求部分
Self-hosted metasearch and grounding engine for AI agents, based on SearXNG. Rust, JSON API, optional page text.
A lightweight, local-first, and free experiment tracking library from Hugging Face 🤗
Neo4j graph construction from unstructured data using LLMs
Auto Ontology is a Python framework for building semantic, graph-based reasoning layers over data. It enables deterministic query generation, better context retrieval, and more explainable AI for L…
Code for Latent Sparse Attention: Towards Subquadratic Ultra-Long Context Attention
🔥 人人可用的开源 BI 工具,数据可视化神器。An open-source BI tool alternative to Tableau.
C++/CUDA single-GPU inference engine for Qwen3.8 (incl. Qwen3.8-Flash-Next with offloaded experts) on the RTX 5090; grew from NInfer
A Cloud Native traffic orchestration system. (CNCF Project)
Monitorable, gracefully restarting, self-upgrading binaries in Go (golang)
Zero downtime restarts for go servers (Drop in replacement for http.ListenAndServe)
Qwen3.5-2B with a SIMT GPU inside its weights, 45 compiled layers in front of Qwen’s own, using its Gated DeltaNet layers as registers and memory.
Craft Anything: understand how any software works, and craft your own.
An LLM running on an NPU inside an LLM. Karpathy's stories260K writing stories on a vector unit compiled into Qwen3.5-4B's weights.
UEFI pre-driver NVIDIA GPU unlocker for Windows Linux Hackintosh and all EFI-bootable system (Rust): SEC2 scrubber -> FWSEC/WPR2 -> signed Booter -> V67 four-write payload, read-back verified. Veri…
Static recompilation of The Legend of Zelda: Tears of the Kingdom to native Windows and Linux x86-64, with a Vulkan renderer. Game files not included.
Fastest, smallest, and fully autonomous AI assistant infrastructure written in Zig
reverse engineering Gemini's SynthID detection
Open-source plugin for designing and reviewing software with AI agents