molmoact2-libero-nf4

Automate Franka Panda manipulation tasks with MolmoAct2 in LIBERO simulation.

Updated Jul 5, 2026
One-click install
npx skills add https://github.com/bensonlee5/openral --skill molmoact2-libero-nf4
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: molmoact2-libero-nf4
Source: https://github.com/bensonlee5/openral/tree/main/rskills/molmoact2-libero-nf4
Command: npx skills add https://github.com/bensonlee5/openral --skill molmoact2-libero-nf4

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires openral, molmoact2, transformers, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill automates complex robotic manipulation tasks, enabling robots to perform precise actions like picking, placing, opening, and closing objects in various scenes.

Core Features & Use Cases

  • Robotic Manipulation: Perform tasks such as picking up objects, placing them, opening drawers, and closing bowls.
  • Embodiment Support: Supports the Franka Panda robot in simulation environments.
  • Use Case: Imagine you need a robot to perform a series of tasks in a kitchen environment, such as picking up a bowl, placing it on a table, and then opening a drawer. This Skill can automate these tasks with high accuracy.

Quick Start

Use the molmoact2-libero-nf4 skill to perform a series of tasks on a Franka Panda robot in the MuJoCo-backed LIBERO simulator.

Frequently Asked Questions about molmoact2-libero-nf4

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate robotic manipulation tasks in a simulation environment?

Automate robotic manipulation tasks in simulation using a vision-language-action policy like MolmoAct2. This enables robots to perform precise actions such as picking, placing, opening, and closing objects with high accuracy.

Does MolmoAct2 support the Franka Panda robot?

Yes, MolmoAct2 supports the Franka Panda robot. It operates within the MuJoCo-backed LIBERO simulator to handle complex manipulation tasks in various simulated scenes.

What do I need to run vision-language-action policies for robotic manipulation?

To run vision-language-action policies for robotic manipulation, you need OpenRAL, a compatible robot hardware abstraction layer (HAL), and the MuJoCo-backed LIBERO simulator configured for your environment.

How do I perform kitchen tasks like opening drawers with a Franka Panda robot?

Perform kitchen tasks like opening drawers with a Franka Panda robot by applying MolmoAct2. The policy translates visual and language inputs into precise robotic actions for picking and placing objects.

What are the limitations of using MolmoAct2 for robotic manipulation?

MolmoAct2 for robotic manipulation is currently limited to simulation environments, specifically requiring the MuJoCo-backed LIBERO simulator and the Franka Panda embodiment rather than direct physical hardware.