Stars
TimeCopilot: the GenAI Forecasting Agent. Built on LLMs and Time Series Foundation Models, it lets you forecast, cross-validate, and detect anomalies using multiple foundation models through a sing…
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Open source reference design for implementing Loop-1, an API for real-time reinforcement learning
Knowledge-based, Content-based and Collaborative Recommender systems are built on MovieLens dataset with 100,000 movie ratings. These Recommender systems were built using Pandas operations and by f…
LLM/VLM gaming agents and model evaluation through games.
An autoregressive character-level language model for making more things
Our "hello, world!" -- a simple clam-like agent that can learn when to open to particular stimuli
multi-class image classification
I created this object as I wanted to make a customizable Stewart Gogh Platform Simulator.
The official Python library for the AO Labs API, compatible with ao_core
Train transformer language models with reinforcement learning.
an open source dataset and generation pipeline for Large-Scale Reinforcement Learning
Fully open reproduction of DeepSeek-R1
A Self-adaptation Framework🐙 that adapts LLMs for unseen tasks in real-time!
A Python-based framework for building multi-agent systems with LLMs. Currently in pre-launch alpha.
Docs for api.aolabs.ai and ao_core via a readme.com integration
Playing Pokemon Red with Reinforcement Learning
This repository has implementations of various alternatives to backpropagation for training neural networks.