balloch

gpt-engineer

Specify what you want it to build, the AI asks for clarification, and then builds it.

LocalAI

:robot: The free, Open Source OpenAI alternative. Self-hosted, community-driven and local-first. Drop-in replacement for OpenAI running on consumer-grade hardware. No GPU required. Runs gguf, transformers, diffusers and many more models architectures. It allows to generate Text, Audio, Video, Images. Also with voice cloning capabilities.

RWKV-LM

RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.

mamba

Mamba SSM architecture

burn

Burn is a new comprehensive dynamic Deep Learning Framework built using Rust with extreme flexibility, compute efficiency and portability as its primary goals.

tigerbeetle

The distributed financial transactions database designed for mission critical safety and performance.

Pearl

A Production-ready Reinforcement Learning AI Agent Library brought by the Applied Reinforcement Learning team at Meta.

brax

Massively parallel rigidbody physics simulation on accelerator hardware.

purejaxrl

Really Fast End-to-End Jax RL Implementations

octo

Octo is a transformer-based robot policy trained on a diverse mix of 800k robot trajectories.

gymnax

RL Environments in JAX 🌍

evosax

Evolution Strategies in JAX 🦎

dreamerv3-torch

Implementation of Dreamer v3 in pytorch.

RT-2

Democratization of RT-2 "RT-2: New model translates vision and language into action"

daydreamer

DayDreamer: World Models for Physical Robot Learning

neural-astar

Official implementation of "Path Planning using Neural A* Search" (ICML-21)

gated-path-planning-networks

Gated Path Planning Networks (ICML 2018)

openrlbenchmark

xland-minigrid

JAX-accelerated Meta-Reinforcement Learning Environments Inspired by XLand and MiniGrid 🏎️

Belief-Propagation

Overview and implementation of Belief Propagation and Loopy Belief Propagation algorithms: sum-product, max-product, max-sum

RT-X

Pytorch implementation of the models RT-1-X and RT-2-X from the paper: "Open X-Embodiment: Robotic Learning Datasets and RT-X Models"

PGMax

Loopy belief propagation for factor graphs on discrete variables in JAX

cleanba

CleanRL's implementation of DeepMind's Podracer Sebulba Architecture for Distributed DRL

quadra

Quadra: Effortless and reproducible deep learning workflows with configuration files.

diamond_env

Standardized Minecraft Diamond Environment for Reinforcement Learning

VCT

[NeurIPS 2022] code for "Visual Concepts Tokenization"

dm_env_wrappers

Standalone library of frequently-used wrappers for dm_env environments.

llrl

Lipschitz Lifelong RL

TinyRL

Minimalist RL implementation on Tinygrad

Neural-Planner