Dream-1

00:00 / 01:59

Launch video

Give Dream-1 a new bimanual robot with parallel grippers, connect it to our API, and it can start performing tasks out of the box. No fine-tuning, no demonstrations from that robot, and no machine learning expertise required.

This is an important step toward general-purpose robot intelligence.

Today, Dream Labs is also coming out of stealth with $90M in seed funding and making Dream-1 available to people all around the world through a public API.

Dream-1 controls robots it has never seen, on tasks it was never shown, in places it has never been, from $3/hour.

For decades, robotics has been stuck in a chicken-and-egg problem: a robot needs to be useful before people want to buy it, but making it useful requires data from that exact robot, and that data only exists once enough people start using it. Dream-1 is our first step toward breaking that loop.

Self-driving found a way around this cold-start problem. Cars were useful from day one with zero autonomy, so millions of people drove them every day and generated the data needed to train increasingly capable models. Most other robots never had that advantage.

First, robot hardware is getting cheap enough to reach far more people. A capable bimanual arm setup can now cost as little as $2k1.

Second, a robot may no longer need a large dataset of its own before it can be useful. If a model can generalize zero-shot to unseen environments, tasks, and even robots, a new robot can start with useful capabilities.

Put those together and the flywheel can finally start. Cheaper hardware puts more robots into the world. Generalizable models make those robots useful earlier. Useful robots generate more data, and that data makes the models better for the next robot.

Robot hardware is getting cheap faster than anyone expected. See the robots above, where 7 semi-humanoid robots cost less than $15k, a price tier that barely existed a year ago. At the far end of the price curve, Hugging Face's $399 Microduck sold more than 10,000 units within 4 days of its launch in late August2. We believe the robotics take-off will start with robots like these.

Wheels, two arms, parallel grippers; a tier that barely existed a year ago.

That's because their buyers are consumers, prosumers, and small teams, not enterprises. An enterprise buyer is making a spreadsheet decision. If the robot doesn't beat a person on cost, speed, or reliability, it doesn't get bought; that's a high bar to clear. Consumers are different. 10,000+ people just paid $399 within 4 days for a robot whose main job is to be delightful and cute: it walks, waddles, and roller-skates. Somewhere between that and a fully capable home robot is a sweet spot, a robot affordable enough to be an easy yes and useful enough to earn its place in the home. Once robots hit that point, we think adoption starts to compound, and every robot in a home becomes a source of new training data. Imagine two Microducks folding your laundry, using their beaks as grippers.

In February 2026, our team released DreamZero, the paper that introduced World Action Models3. Since then, the community has adopted WAMs as one of the most promising paradigms in robot learning. At that time, the most surprising result for us was when after post-training DreamZero on just 30 minutes of YAM robot data, we saw it generalize zero-shot to tasks it had never seen. That kind of generalization used to take hundreds or even thousands of hours of embodiment-specific data. If 30 minutes of data from a given robot was enough to transfer general-purpose task knowledge to that robot, breaking the chicken-and-egg loop no longer looked impossible. Combined with the hardware wave above, the timing felt right. That's when we decided to start Dream Labs.

After six months of building, we're excited to share a new research breakthrough that was only made possible through world action models: early signs of zero-shot embodiment generalization.

Dream-1 is our first World Action Model available through a public API that can be used all around the world. Out of the box, it can control unseen robots for unseen tasks in unseen environments.

BitRobotShenzhen, ChinaPull out a tissue 1 of 4

CortexSingaporeStack the white cup on top of the pink cup 1 of 2

EastworldKL, MalaysiaPlace the apple in the brown box 1 rollout

Hugging FaceParis, FrancePick up the red cube and put it in the green container 1 rollout

XDOFJakarta, IndonesiaFind the marker and pick it up 1 rollout

RoboCurveSan Francisco, USAStand all three bottles upright 1 of 4

Scale AISan Francisco, USAStack the cubes into a single tower 1 of 9

Robo Inc.Los Angeles, USAMove chips to tray 1 rollout

Lift a test tube from the loose rack 1 rollout

1–13 of 13

Autonomous · 4×

Fold the dress.

Clear the dishes from the countertop into the sink.

Pull the cap off of the blue highlighter.

Grab the cat litter scoop and scoop inside the litter box.

Restock the food cans from the box onto the shelf.

Put the egg in the empty spot in the egg carton.

Wipe the countertop with the blue sponge.

Pour the fruits from the bowl on the left to the bowl on the right.

Slide the middle book out from the stack of three books.

Dry the plate with the towel and place it on the drying rack.

Open the box, take out the pink jump rope and close the lid.

Use the knife to push the chopped carrot to the right side of the cutting board.

1–9 of 18

Unseen Tasks Dream-1 was able to do. Autonomous. 8x speed at the beta testers’ sites, 4x in-house.

04.1

We want generalizable robotics to be accessible to anyone with a robot, not just large labs. So we designed Dream-1 to be as close to plug-and-play as possible. Connect your robot, point it at the API, and run. No machine learning background is needed to get started. Every week, we run internal hackathons to keep time-to-deploy as short as possible. Getting started tutorial

import dream

client = dream.DreamClient( api_key=<API_KEY>, ) client.policy({"checkpoint": "dreamlabs/dream-1"}) client.set_observation(observation) action = client.get_action() client.close()

Condensed client side code

Dream-1 can zero-shot generalize to many bimanual, parallel-gripper robots. Here are some we've tested. It can even control the original PR2, a general-purpose bimanual research robot released 18 years ago. Note that no embodiment-specific data was used to get these rollouts.

AI WorkerROBOTISTurn the large dial so its pointer points at the red mark

ALOHATrossen (Interbotix)Press the big red mushroom button

ARX X5ARXTip the cereal box onto its side

BaxterRethink RoboticsPress the big red mushroom button

Bracket BotBracket BotTip the plastic bottle onto its side

Franka Research 3, two armsFranka RoboticsTip the cereal box onto its side

Galaxea A1ZGalaxeaPush the tennis ball into the basket

Gen3, two armsKinovaPlace the umbrella into the bucket

LBR iiwa 14KUKAPick up the tape and place it in the round white bin

MantisBlue WormPull the cable out of the box handle

Metal ArmMakerModsPut the tape roll over the bottle

OpenYAMAnvil RoboticsPick up the knife by its handle, never the blade, and place it in the tray

PiPER, two armsAgileX RoboticsLift the pot by its two handles, carry it to the red mat and set it down level

PR2Willow GaragePress the big red mushroom button

reBot B601-DMSeeed StudioPick up the knife by its handle, never the blade, and place it in the tray

Sawyer, two armsRethink RoboticsClose the top drawer

SO-101Hugging FaceTip the plastic bottle onto its side

Trossen WorkbenchTrossen RoboticsPick up the knife by its handle, never the blade, and place it in the tray

Unitree R1UnitreePut the small bowl inside the large bowl

UR5e, two armsUniversal RobotsPick up the mug by its handle and place it on the tray

WidowX 250, two armsTrossen (Interbotix)Press the big red mushroom button

xArm 7, two armsUFactoryTip the plastic bottle onto its side

YAM + UMI gripperI2RT x GenRobot.AITip the plastic bottle onto its side

YAM-7I2RTTip the plastic bottle onto its side

OpenYAMAnvil RoboticsDrape the hand towel over the rack

OpenYAMAnvil RoboticsHide a dumpling under the towel

YAM + UMI gripperI2RT x GenRobot.AIPull the towel to bring the plate to the center of the table

Maker ArmMakerModsPut the sponge in the dog bed

Metal ArmMakerModsGo ahead and put the banana in the bowl

reBot B601-DMSeeed StudioGo ahead and put the banana in the bowl

YAM + Enpire grippersI2RT x EnpirePut the straw into the bottle neck

Metal ArmMakerModsPut the grape into the pan

OpenYAMAnvil RoboticsClose the top drawer

reBot B601-DMSeeed StudioPush the tennis ball into the basket

OpenYAMAnvil RoboticsPut the baby bottle in the pen holder

Maker ArmMakerModsPull the towel to bring the plate to the center of the table

OpenYAMAnvil RoboticsGrab a handful of cotton balls and put them in the cup

OpenYAMAnvil RoboticsSet the tennis ball on top of the upside-down mug

Metal ArmMakerModsStack the bowl inside the small pot

OpenYAMAnvil RoboticsPut the plate on top of the basket like a lid

OpenYAMAnvil RoboticsHang the headphones on the hook

YAM + UMI gripperI2RT x GenRobot.AIPut the fruit that is not the kiwi in the basket

reBot B601-DMSeeed StudioPick up the mango and place it in the bowl

Vega 1 Pro + YAM GripperDexmate x I2RTPick up all markers one by one and put into black pencil holder using both arms

Unseen Robots Dream-1 was able to control. 4x speed on real robots, 3x in simulation.

This is one of the first reported zero-shot generalizations to completely unseen robot embodiments.4 If you have a bimanual parallel-gripper robot, try prompting Dream-1 and let us know how it goes. Zero-shot performance depends partly on your robot's inverse kinematics (IK) solver, so we've written a guide to help you get the most out of it. IK guide. Performance also varies across robots. Below, we break down zero-shot performance in simulation and on real robots.

Below, we explain how zero-shot embodiment generalization works and where it falls short. We then show how one-shot embodiment learning closes that gap.

Two ways to control a robot: joints or end-effectors. Robot policies commonly output joint angles, which ties them to one specific robot's body. Dream-1 can do the same for the embodiments it supports natively, but it can also predict end-effector (EEF) poses: where each gripper should be and whether it should be open or closed. Every robot with two arms and parallel grippers shares that EEF action space, and its own IK solver turns the poses into joint commands. That shared interface gives Dream-1 a common way to command robots it has never seen, but on its own it isn't enough to make zero-shot transfer work.

Why does this work? Dream-1 sees the world through three cameras: a head view and a wrist view on each arm. Prior work on the Universal Manipulation Interface (UMI) showed that policies can transfer zero-shot across robot arms when every arm uses the same gripper and the policy relies only on wrist cameras5. From the wrist's point of view, the robots look identical. But that shortcut has a hard limit. It only works when the gripper hardware matches exactly, and it gives up the head camera's view of the whole scene.

World Action Models remove that limit. A WAM learns to predict video and actions together, so controlling a robot and imagining what that robot will do are the same problem. And every robot shows up the same way: as pixels. The head camera sees a UMI gripper, a two-finger gripper or an arm Dream-1 has never met as nothing more than shapes moving through a scene, which makes video the one representation every robot type shares. If Dream-1 can predict what a robot will look like as it completes a task, it can produce the actions that get it there. That’s why it can control robots with grippers that look nothing like UMI’s, and even entirely new bodies seen through the head ca