Two years ago, we released Genesis, a universal physics engine for...

Today, Iโm excited to announce ๐ Eden โ a robot learning framework built from the ground up for agents, unleashing full potential of Genesis.
One task definition. From simulation to real robots. Sim-to-sim and sim-to-real just got easier.
Coding agents build tasks 1.6โ4ร faster than in Isaac Lab.
๐งต 1/11
Bring your trainer: rsl_rl, rl_games, skrl, Stable-Baselines3.
Bring your benchmark: LIBERO, robosuite, SIMPLER, PolaRiS, and more โ already ported.
eden train --task
4/11
G1, Oli, Go2, Franka, UR5e, xArm7, iiwa14, WidowX, YAM, LEAP, Inspire, XHand, Wuji, Sharpaโฆ
Plus 950+ objects to put in front of them.
5/11
SONIC, BeyondMimic, TWIST2, HOMIE, AMO, ProtoMotions, MetaMotivo, ฯ0.5, GR00T, Octoโฆ
Run them out of the box to try, supervise, or generate data:
eden inference --policy <policy name> --vis
6/11
โญ github.com/embodied-ai-neโฆ
๐ embodied-ai-nexus.github.io/Eden
pip install eden-world
Star, fork, and explore! What should we build next??
