- Amsterdam, Netherlands
- @seoul_engineer
Lists (4)
Sort Name ascending (A-Z)
- All languages
- ANTLR
- AppleScript
- Arduino
- Assembly
- Astro
- Bikeshed
- Bison
- Brainfuck
- C
- C#
- C++
- CMake
- CSS
- Clojure
- CodeQL
- CoffeeScript
- Common Lisp
- Crystal
- Cuda
- Cython
- D
- Dart
- Dockerfile
- Eagle
- Elixir
- Elm
- Emacs Lisp
- Go
- Groovy
- HCL
- HTML
- Haskell
- Isabelle
- Java
- JavaScript
- JetBrains MPS
- Julia
- Jupyter Notebook
- KiCad Layout
- Kotlin
- LLVM
- LiveScript
- Lua
- MATLAB
- Makefile
- Markdown
- Nemerle
- NewLisp
- Nunjucks
- OCaml
- Objective-C
- Objective-C++
- PHP
- Perl
- PostScript
- PowerShell
- Processing
- Prolog
- Protocol Buffer
- Puppet
- Python
- QML
- R
- REXX
- Racket
- Raku
- RobotFramework
- Rocq Prover
- Roff
- Ruby
- Rust
- SCSS
- SMT
- Scala
- Shell
- Slash
- Slice
- Smalltalk
- Starlark
- SuperCollider
- Swift
- SystemVerilog
- TLA
- TXL
- TeX
- TypeScript
- VHDL
- Vala
- Verilog
- Vim Script
- Vue
- Zig
- hoon
- q
Starred repositories
FineEnvs — RL Environments 101: building and scaling RL environments in the age of LLMs
⌥ Coding agent with the IDE wired in. Built by Stencil Labs.
mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking current sota approaches while being all local
Karpathy's LLM Wiki pattern as a minimal, agent-agnostic skill
A local inference engine for Apple silicon, built around the model.
Procedurally generated Chinese landscape painting.
Reverse engineer anything with agents, from app behavior down to native binaries.
A Control Arena setting for evaluating agents inserting backdoors while refactoring full repos.
Open source inference engine that tunes its kernels on your hardware to find the fastest way to run each model. 2x faster than Ollama. Works on Apple Silicon, NVIDIA, AMD, Intel, or just a CPU.
Agentic RL on Any Harness at Scale
Fine-tune open-source models with Tinker from inside Pi — managed improve loops, data prep, evals, smoke tests, deploy snippets, and checkpoint chat.
SkillForge: Self-Distilling Agents for Project-Specific Issue Resolution
Rethinking Code Editing for Efficient Software Engineering Agents
A workspace for terminal coding agents: run any agent CLI, review its changes from diff to merged PR, and let it draw the UI you need beside the session.
Distributed 56M-parameter LLM inference across 3 ESP32-S3 boards via ESP-NOW , Split-PLE + KV cache, fully offline.
Turn your coding agents into research agents
🧠 Train a 64M-parameter LLM from scratch in just 2h!
Container-free RL framework for training software engineering agents
Turn any technical book PDF into a Claude Code skill — ready to study, reference, and use while you work.
The open-source agent for CI/CD reliability.
Fast Rust library for PDF inspection, classification, and text extraction. Intelligently detects scanned vs text-based PDFs to enable smart routing decisions.
Persistent memory system for Claude Code — make your AI remember everything across sessions. Ready-to-use templates, zero dependencies.
Export and Share your ChatGPT conversation history
A browser bookmarklet for exporting conversations with ChatGPT, Gemini and Claude as either markdown or HTML files.
Sync Claude Code sessions across devices using Cloudflare R2 with end-to-end encryption
A simple, modern and secure encryption tool (and Go library) with small explicit keys, no config options, and UNIX-style composability.