RedTachyon

coltra-rl

A modular implementation of PPO, and soon hopefully other algorithms.

llm-zth

redtachyonme

anterion

Open-source software engineer

cleanrl

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

CodeSnap

🦀️📸 Pure Rust tool to generate beautiful code snapshots, provide CLI and Library

Cradle

The Cradle framework is a first attempt at General Computer Control (GCC). Cradle supports agents to ace any computer task by enabling strong reasoning abilities, self-improvment, and skill curation, in a standardized general environment with minimal requirements.

decimal-float-toy-vite

Deep-Live-Cam

real time face swap and one-click video deepfake with only a single image (uncensored)

dotfiles

Dot files for Evan Chen (Arch Linx on i3)

hanzi-writer-data

The data used by Hanzi Writer

instructor

structured outputs for llms

LaVague

Copilot for web automation

llm-playground

WiP tool to interact with locally trained models

llm.c

LLM training in simple, raw C/CUDA

lm-evaluation-harness

A framework for few-shot evaluation of language models.

mincv

OSWorld

OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments

pong-wars

PRIME

PufferLib

Simplifying reinforcement learning for complex game environments

redtachyon

SWE-agent

SWE-agent: Agent Computer Interfaces Enable Software Engineering Language Models

task-standard

METR Task Standard

TinyLlama

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

torchtune

PyTorch native post-training library

TPU-Alignment

Fully fine-tune large models like Mistral, Llama-2-13B, or Qwen-14B completely for free

typarse

Simple type-based argument parsing

vimGPT

Browse the web with GPT-4V and Vimium

wildcats-ai

This will one day be an actually working AI agent