- Republic of Korea
- https://hahwul.com
- @hahwul
- hahwul_
Highlights
Lists (1)
Sort Name ascending (A-Z)
- All languages
- Assembly
- BlitzBasic
- C
- C++
- CMake
- CSS
- CodeQL
- Crystal
- Dart
- Dockerfile
- Elixir
- Erlang
- F#
- GLSL
- Go
- HCL
- HTML
- Inno Setup
- Java
- JavaScript
- Jupyter Notebook
- Just
- Kotlin
- LLVM
- Lua
- MDX
- Makefile
- Markdown
- Meson
- Nim
- Nix
- Nunjucks
- Nushell
- OCaml
- Objective-C
- Objective-C++
- PHP
- Pascal
- Perl
- PowerShell
- Python
- Ruby
- Rust
- SCSS
- Scala
- Shell
- Starlark
- Svelte
- Swift
- Tree-sitter Query
- TypeScript
- V
- Verilog
- Vim Script
- Vue
- XSLT
- YARA
- Zig
Starred repositories
A background task runner for crystal applications supporting periodic (CRON) and manually queued jobs
⚗ Experimental Hermes Agent plugins built by Nous Research but not supported: community tier in the plugin catalog, up for adoption.
An agent skill for creating detailed, interactive isometric illustrations of real-world machines and complex systems. Generates polished SVGs with optional WebGL shaders and 3D effects.
Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA
Reverse engineer anything with agents, from app behavior down to native binaries.
bsysop / jwt-hack
Forked from hahwul/jwt-hack🔩 jwt-hack is tool for hacking / security testing to JWT. Supported for En/decoding JWT, Generate payload for JWT attack and very fast cracking(dict/brutefoce)
Specification and documentation for the Universal Commerce Protocol (UCP)
Fast Ansible-compatible automation in Crystal - no Python required
A smarter, self-hosted AI assistant — multi-user, multi-agent.
Use pstack with claude, codex, pi - Skills and principles for rigorous AI-assisted engineering
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Set of 26 benchmarks for iyi language, in one file.
ONCE Campfire in Rust: one binary, the Rails app's data, 19–44× faster
Jev-compatible API server for open decision models. Ollama for decision models: pull and serve 29 model families (Laya, pplx-decider, Clef, Winnow, coba...) locally or self-hosted behind /v1/system…
Jev-like family of decision models built on top of Qwen3.5/3.8 you can train and run on your own
Z.ai's coding agent harness. Powerful, intelligent, extensible.
AI-powered MCP server for Flipper Zero. Control SubGHz, NFC, RFID, IR, BLE, GPIO, and more over WiFi using Claude or any MCP client.
Worktrunk is a CLI for Git worktree management, designed for parallel AI agent workflows
HTTP/2 Protocol Implementation for the Crystal Language
Codex/ChatGPT multiple account load balancer & proxy with usage tracking, dashboard, and OpenCode-compatible endpoints
The ripgrep of AI context: a zero-dependency C++23 CLI + MCP server for coding agents. Find what you want without reading the repo, then check you built what you meant — blast radius, tests-to-run,…
Credential-scoped AI usage, context, and cache in Herdr for Claude, Codex, Grok, Agy, OpenCode, Pi, omp, Devin, Muse, MiMo, Kilo, Antigravity, and Cursor.
Generates context-aware workspace and tab names for Herdr.
Who's working, who's waiting on you — grouped by project, each agent in its vendor's logo and colour. Worktrees nest under their repo, rows order by activity, idle sessions fade. Light and dark.