OpenMHSindependent draft 0.9
Playground
Open menu

Robots · Simulation · robot arm manipulation

Surreal Robotics Suite DoorOpen environment

Surreal Robotics Suite DoorOpen environment, adapted from stanfordvl/lasersuite. It reads observation, tick, seed, reward and 1 more; runs reset_world and step. reset_world: reset the simulated world to a scenario start state and return the initial observation. When a seed is supplied the endpoint records it in the receipt; otherwise the endpoint's declared default seed applies. A simulator: the market serves it with a stand-in that needs no simulator install.

simulatedRisk R0MITcontract_checkedserved on the fake backend
openai4s lab add robots/stanfordvl__lasersuite
All install options REFERENCE.md Upstream repository Registry record

Install

Three ways to run this device. Each one serves its fake backend: no instrument, no simulator install and no upstream checkout.

OpenAI4S (one command)

shell
openai4s lab add robots/stanfordvl__lasersuite

Installs the device into the OpenAI4S Lab on its fake backend and starts it. First time? See setup below.

Or, in the workbench, open the Lab tab → Market → Install.

Standalone MHS endpoint

shell
git clone --depth 1 https://github.com/PKU-YuanGroup/OpenMHS.git && cd OpenMHS
PYTHONPATH=MHS/sdk/src python3 -m mhs serve robots/stanfordvl__lasersuite --port 7400
# in a second terminal, from the same directory:
PYTHONPATH=MHS/sdk/src python3 -m mhs describe --endpoint http://127.0.0.1:7400

Serves the device as an MHS endpoint on port 7400 from an OpenMHS clone (Python 3.10 or later, standard library only); describe prints what it offers.

Any MCP host (Claude Desktop, Cursor, …)

mcp configuration
{
  "mcpServers": {
    "lasersuite": {
      "command": "python3",
      "args": [
        "-m",
        "mhs",
        "serve",
        "robots/stanfordvl__lasersuite",
        "--mcp"
      ],
      "env": {
        "PYTHONPATH": "/path/to/OpenMHS/MHS/sdk/src"
      }
    }
  }
}

Add this server to the host's MCP configuration and replace /path/to/OpenMHS with the path of your OpenMHS clone. The host starts the server and talks to it on stdin and stdout.

What it does

Measures

  • observation
  • tick
  • seed
  • reward
  • terminated

Adjusts

Nothing declared.

Actions

reset_world
Reset the simulated world to a scenario start state and return the initial observation. When a seed is supplied the endpoint records it in the receipt; otherwise the endpoint's declared default seed applies.
step
Advance the simulated world by a bounded number of fixed timesteps, optionally applying an action for each step, and return the resulting observation and terminal flags.

Names as the driver declares them. Units, limits and the safety declaration are in the package's REFERENCE.md.

First-time setup

The OpenAI4S workbench with the OpenMHS lab, from a source checkout:

shell
# OpenAI4S workbench with the OpenMHS lab (source checkout)
git clone --recursive https://github.com/PKU-YuanGroup/OpenAI4S.git
cd OpenAI4S && ./setup.sh && source .venv/bin/activate
openai4s lab add robots/stanfordvl__lasersuite
openai4s serve        # open the Lab tab

The standalone endpoint and the MCP server need only an OpenMHS clone and Python 3.10 or later. More in the market's getting-started guide and on the OpenAI4S host page.

Source and evidence

Pinned commit
8b78c3d202f2
Licence
MIT
Stars
13
Evidence
contract_checked on the fake backend
Backends
fake

The driver package MHS/drivers/robots/stanfordvl__lasersuite wraps the upstream code at the pinned commit. Its REFERENCE.md documents the full contract: every value, action, unit, limit and the safety declaration.