RepoAlerts

ArcheOne-AI/RoboScript

Agent

Can I trust it?

Worth a closer look before you use it.

  • Warnings Check

    Very new: it was created 12 days ago. Wait a little before installing it.

  • Stars from real accounts No data

    We haven't checked its stars for fakes yet.

  • Active OK

    Last change 6 days ago.

  • Licence OK

    Apache-2.0: you can use it for free, also in a commercial product. Keep the licence notice.

Quick checks from public data. They help, but they are no guarantee.

What it is

Agent framework for robot manipulation that learns a task from one demonstration by rehearsing it in a simulator and storing the learned knowledge in the model's context rather than in weights. Validated on dual-arm tabletop manipulation with the RoboTwin 2.0 benchmark and…

Who it's for

Robotics and AI researchers working on embodied agents and robot manipulation with frozen foundation models

How to use it

Install

uv sync --all-packages

From its README. Check it there before running it.

Ask your AI to set it up

Paste this into Claude, ChatGPT or your coding assistant.

Help me install and set up ArcheOne-AI/RoboScript in my project. Follow its README: https://github.com/ArcheOne-AI/RoboScript. Explain each step and check it is safe before running anything.

Star curve

299From 0 to 299 stars between 5 Nov 2026 and 17 Nov 2026.

Get alerts for repos like this

We'll email you when something in AI agents starts rising. Free, once a week, only what matches.

What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy

For maintainers

Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.

[![ArcheOne-AI/RoboScript on RepoAlerts](https://repoalerts.com/badge/ArcheOne-AI/RoboScript.svg)](https://repoalerts.com/repo/ArcheOne-AI/RoboScript?ref=badge)
Share on X

  • shengshu-ai/Motus2

    A research world model for robotic dexterous manipulation that uses one shared-weight model as a policy proposing action chunks, a simulator predicting their visual outcomes, and an evaluator scoring

    AI agentsPython · 555 stars · +145 this week · 67 days old

  • OpenSenseNova/SenseNova-RoboRSI

    A framework for building, evaluating and iteratively improving embodied agents on a shared runtime. It connects models, prompts, skills and robot tools, runs benchmark environments with native scoring

    AI agentsPython · 817 stars · +226 this week · 39 days old

  • BinceQu/RoboHarness

    A harness that lets an LLM agent control a robot in embodied tasks. The agent marks points on a 2D image, receives their tracked positions through optical-flow tracking and depth back-projection, and

    AgentAI agentsPython · 521 stars · +193 this week · 41 days old

  • skild-ai/steel

    A rigid-body physics solver for scalable robot simulation of manipulation tasks, developed by Skild with NVIDIA and distributed as part of Newton. The README reports higher simulation throughput than

    LibraryModels & inferencePython · 235 stars · +131 this week · 8 days old

  • zengxiong111/Foundation_of_Embodied_AI

    Chinese and English teaching materials for a planned embodied AI course, with 17 topics covering ROS 2, camera calibration, robot dynamics, Isaac Sim and MuJoCo, reinforcement learning (PPO, SAC), Flo

    ResourceAI agents245 stars · +14 this week · 32 days old

  • eust-w/opengeniemaster

    A zero-dependency Python framework that exposes embodied robot execution, multimodal guidance, physical feedback and task continuity as an MCP server, so coding agents can drive multi-robot work. It a

    AgentAI agentsPython · 461 stars · +298 this week · 21 days old