npx claudepluginhub plurigrid/asi --plugin asiThis skill uses the workspace's default tool permissions.
**Trit**: -1 (MINUS - specification/verification)
Provides hardware specifications, MJCF simulation models, and deployment configurations for K-Scale Labs' K-Bot humanoid robot. Useful for robotics simulation, control, and integration.
Guides training RL agents with Stable Baselines3 (PPO, SAC, DQN, TD3, DDPG, A2C), custom Gym environments, callbacks for monitoring, vectorized envs for parallel training, and deep RL workflows.
Guides training RL agents with Stable Baselines3 algorithms (PPO, SAC, DQN, TD3, A2C) using Gymnasium environments, custom env creation, callbacks, and optimization.
Share bugs, ideas, or general feedback.
Trit: -1 (MINUS - specification/verification) Color: #8CC136 (Lime Green) URI: skill://zeroth-bot#8CC136
Zeroth Bot (Z-Bot) is a 3D-printed open-source humanoid robot platform designed for sim-to-real research and RL experimentation. An affordable entry point for humanoid robotics.
┌────────────────────────────────────────────────────────────────┐
│ ZEROTH BOT (Z-BOT) │
├────────────────────────────────────────────────────────────────┤
│ │
│ Height: ~40cm │
│ Weight: ~2kg │
│ DOF: 12 joints │
│ │
│ Frame: 3D printed (PLA/PETG) │
│ Actuators: Servo motors │
│ Cost: ~$500 BOM │
│ │
│ Ideal for: │
│ ├── Learning sim-to-real transfer │
│ ├── Testing RL policies at low cost │
│ ├── Educational robotics │
│ └── Rapid prototyping │
│ │
└────────────────────────────────────────────────────────────────┘
| Component | Quantity | Notes |
|---|---|---|
| Servo motors | 12 | Standard hobby servos |
| 3D printed parts | Full set | STL files provided |
| MCU | 1 | ESP32 or Teensy |
| IMU | 1 | MPU6050 or similar |
| Power | 1 | 2S-3S LiPo |
from ksim.robots.zbot import ZBotConfig
from ksim import PPOTask
class ZBotWalking(PPOTask):
robot = ZBotConfig(
model_path="zbot.mjcf",
servo_config={
"kp": 50.0,
"kd": 5.0,
"torque_limit": 5.0, # Smaller than K-Bot
}
)
# Faster training due to simpler robot
training_config = {
"num_envs": 2048,
"learning_rate": 5e-4,
}
zeroth-bot (-1) ⊗ kos-firmware (+1) ⊗ mujoco-scenes (0) = 0 ✓
kbot-humanoid (-1): Larger flagship humanoidksim-rl (-1): RL training librarykos-firmware (+1): Firmware (kos-zbot variant)urdf2mjcf (-1): Model conversionZ-Bot has a web-based control interface:
// From zbot-web-frontend
import { ZBotController } from '@kscale/zbot-web';
const controller = new ZBotController({
endpoint: 'ws://zbot.local:8080',
});
await controller.connect();
await controller.setJointPositions({
hip_pitch_l: 0.5,
knee_l: -0.3,
});
@misc{zerothbot2024,
title={Zeroth Bot: 3D-Printed Open-Source Humanoid},
author={K-Scale Labs},
year={2024},
url={https://github.com/kscalelabs/zeroth-bot}
}