- Cologne, Germany
- https://pschen.de
- All languages
- ActionScript
- Arduino
- Astro
- C
- C#
- C++
- CSS
- Clojure
- CoffeeScript
- Dart
- Dockerfile
- Elixir
- Emacs Lisp
- Fluent
- GLSL
- Go
- HTML
- Java
- JavaScript
- Jupyter Notebook
- Lua
- MDX
- Makefile
- Nix
- Nunjucks
- Nushell
- Objective-C
- PHP
- Perl
- PostScript
- PowerShell
- Processing
- Python
- R
- Rich Text Format
- Ruby
- Rust
- SCSS
- Shell
- Starlark
- Svelte
- Swift
- TeX
- TypeScript
- Vala
- Vue
- WebAssembly
- XSLT
- Zig
Starred repositories
Fine-tune LLMs on your Mac with Apple Silicon. SFT, DPO, GRPO, Vision, TTS, STT, Embedding, and OCR fine-tuning — natively on MLX. Unsloth-compatible API.
KV cache compression via block-diagonal rotation. Beats TurboQuant: better PPL (6.91 vs 7.07), 28% faster decode, 5.3x faster prefill, 44x fewer params. Drop-in llama.cpp integration.
DFlash: Block Diffusion for Flash Speculative Decoding
Fast and accurate AI powered file content types detection
Lossless DFlash speculative decoding for MLX on Apple Silicon
Exact speculative decoding on Apple Silicon, powered by MLX.
🌰 Terminal-based automated file organizer inspired by Hazel. Watch folders and organize files with rules.
Library for reducing tail latency in RAM reads
Gin is a high-performance HTTP web framework written in Go. It provides a Martini-like API but with significantly better performance—up to 40 times faster—thanks to httprouter. Gin is designed for …
Using BFS & DFS like techniques over LLMs for iteratively exploring the solution search space at scale.
Fast, accurate & comprehensive text measurement & layout
Create stunning demos for free. Open-source, no subscriptions, no watermarks, and free for commercial use. An alternative to Screen Studio.
The best-benchmarked open-source AI memory system. And it's free.
Anthropic-compatible HTTP facade over claude-agent-acp
Join Discord: https://discord.gg/5TUQKqFWd / claw-code Rust port parity work - it is temporary work while claw-code repo is doing migration
Lightweight, cross-platform process sandboxing powered by OpenAI Codex's runtime. Sandbox any command with file, network, and credential controls.
MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.
Vane is an AI-powered answering engine.
a small build system with a focus on speed
PostgreSQL extension for BM25 relevance-ranked full-text search. Postgres OSS licensed.
Ministack: Free, open-source local AWS emulator - 40+ services, Terraform compatible, real databases. Free forever. MIT licensed.
A Go implementation of the Model Context Protocol (MCP), enabling seamless integration between LLM applications and external data sources and tools.
Visualization of all roads within any city
JavaScript in-page GUI agent. Control web interfaces with natural language.
A Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎,预测万物