アキラ's repositories
AdventOfCode2024
My code for [Advent of Code 2024](https://adventofcode.com/2024).
AgentLaboratory
Agent Laboratory is an end-to-end autonomous research workflow meant to assist you as the human researcher toward implementing your research ideas
AntiCrack-DotNet
C# Project contains a plenty of Advanced Anti-Debugging, Anti-Virtualization, Anti Dll-Injection and Anti-Hooking Techniques.
arcadeia
A self-hosted and web-based media archiving, browsing, searching and management solution.
browser-use
Make websites accessible for AI agents
buzz
Buzz transcribes audio from your computer's microphones to text using OpenAI's Whisper
CAG
Cache-Augmented Generation: A Simple, Efficient Alternative to RAG
claude-debugs-for-you
Enable Claude to interactively debug for you via MCP and a VS Code Extension
cudacracker
MD5 hash cracking with CUDA and Rust, implemented from scratch
curiso
Curiso is an infinite canvas for your thoughts
DevDocs
Your Documentation Discovery Engine
DriverStoreExplorer
Driver Store Explorer [RAPR]
ebook2audiobook
Convert ebooks to audiobooks with chapters and metadata using dynamic AI models and voice cloning. Supports 1,107+ languages!
emscripten
Emscripten: An LLVM-to-WebAssembly Compiler
fruitstand
A library for regression testing llm prompts
IRL
Unofficial Implementation of "Imitating Language via Scalable Inverse Reinforcement Learning"
MiceWine-Application
MiceWine is a project that aims to run Windows applications and games on Android smartphones.
n8n
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
Refasmer
The tool to create reference assembly from common assembly.
Rust-for-Malware-Development
This repository contains my complete resources and coding practices for malware development using Rust 🦀.
SmolChat-Android
Running any GGUF SLMs/LLMs locally, on-device in Android
solving-ml-papers
just me trying to implement deep learning concepts in code
tensorzero
TensorZero creates a feedback loop for optimizing LLM applications — turning production data into smarter, faster, and cheaper models.
VectorKernel
PoCs for Kernelmode rootkit techniques research.
verl
veRL: Volcano Engine Reinforcement Learning for LLM
ZLUDA
CUDA on Intel GPUs