RedTachyon

llama-agentic-system

Agentic components of the Llama Stack APIs

arxiv.py

Python wrapper for the arXiv API

ScienceWorld

ScienceWorld is a text-based virtual environment centered around accomplishing tasks from the standardized elementary science curriculum.

PufferLib

Simplifying reinforcement learning for complex game environments

OSWorld

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

vimGPT

Browse the web with GPT-4V and Vimium

pico

Minimal CSS Framework for semantic HTML

alignment-handbook

Robust recipes to align language models with human and AI preferences

Self-Rewarding-Language-Models

This is work done by the Oxen.ai Community, trying to reproduce the Self-Rewarding Language Model paper from MetaAI.

puter

🌐 The Internet OS! Free, Open-Source, and Self-Hostable.

LASER

Code for the paper "LASER: LLM Agent with State-Space Exploration for Web Navigation"

playwright-python

Python version of the Playwright testing and automation library.

anterion

Open-source software engineer

schedule_free

Schedule-Free Optimization in PyTorch

llm.c

LLM training in simple, raw C/CUDA

waitlist-landing-page

simple and effective waitlist page

hugo-theme-dream

🌱 A Hugo theme named Dream.

SWE-agent

SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It solves 12.47% of bugs in the SWE-bench evaluation set and takes just 1 minute to run.

llamafile

Distribute and run LLMs with a single file.

moondream

tiny vision language model

LaVague

Large Action Model framework to develop AI Web Agents

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.

open-interpreter

A natural language interface for computers

typescript-compile

Automatically compile TypeScript to JavaScript on the fly

lag-llama

Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting

taipy

Turns Data and AI algorithms into production-ready web applications in no time.

OLMo

Modeling, training, eval, and inference code for OLMo

pong-wars

GPT-4-LLM

Instruction Tuning with GPT-4

self-rewarding-lm-pytorch

Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI