servo-client

Python and CLI access to Servo's hosted robot policy service.

pip install 'servo-client>=0.4,<0.5'
export SERVO_BASE_URL="https://<your-servo-control-plane>"
servo login
servo account
servo key create --label yam-cell-01
export SERVO_API_KEY="sk_servo_..."

Register a Bimanual YAM on its robot computer, then list compatible models:

servo robot setup yam-cell-01 \
  --config /opt/yam/configs/yam_left.yaml \
  --config /opt/yam/configs/yam_right.yaml \
  --region us-west-2

servo model list yam-cell-01

Run pi0.5 with the calibrated robot object from your application:

import os

import servo
from my_robot_app import open_yam

sv = servo.Servo(
    base_url=os.environ["SERVO_BASE_URL"],
    api_key=os.environ["SERVO_API_KEY"],
)
robot = sv.robots.attach("yam-cell-01", runtime=open_yam)
model = sv.models.get("pi0.5")
deployment = model.deploy(robot=robot).wait(timeout_s=900)
policy = deployment.policy(robot, instruction="place the red lid on the black box")
check = robot.check(policy)
print(check.completed, len(check.chunks), check.steps)
robot.run(policy, seconds=120)

open_yam is the factory function that opens the calibrated YAM runtime. Servo recognizes its camera, joint-state, command, and close methods directly. --config accepts your local hardware configuration files (or placeholder files for testing), which Servo hashes to record an immutable fingerprint. Calibration and device configuration stay in your application.

Save deployment.id and reuse it with sv.deployments.get(deployment_id). Review active capacity with servo deployment list, and stop unused capacity with servo deployment stop <deployment-id>.

Requires Python 3.12+, a Servo control-plane URL, and an organization API key.

Quickstart · Robots and calibration · Robot fleets