Docs

ORA documentation

Run a language model as a robot policy. ORA supplies the robot manual, observation tools, supervised actions, and a record of every episode.

Open Robot-Use Agents · Python 3.11 · OpenAI-compatible and Anthropic APIs

Get started

Install ORA, connect a model API and run a first episode, then a quick run on each simulator.

Use ORA

Run and inspect episodes, free play, real robot cells, remote GPU servers and the command line.

Environments

Set up each simulator in its own environment, then run one task.

Robots and tasks

Each robot's manual as the model reads it, frames and units, and the task lists.

Evaluation

How ORA decides, counts and reports a benchmark outcome.

Concepts

The architecture, how the model's context is assembled, the runtime lifecycle and a glossary.

Reference

Interfaces, evidence formats, context schemes, task files and backend details.

Python API

Plans, policy sessions, environment sessions and action contracts, from the source.

Contribute

Your first hour with the source, the repository rules, testing and the authoring guides.

First episode

From a source checkout, install ORA and check the environment:

uv sync --all-extras --locked
npm ci --prefix ora-pi --prefer-offline --no-audit --no-fund   # Node.js >= 22.19: the agent core
uv run --locked ora doctor

Set ORA_API_KEY in your shell, then run:

uv run --locked ora run --env synthetic

This calls a real model and saves a sealed episode under outputs/quickstart/runs/<run-id>/. Synthetic verifies the agent/runtime connection; its official_success is null.

Complete quickstart and API configuration

Terminal UI, free play and the web page

ORA replaying a LIBERO episode in the terminal

ora watch RUN_ID follows a live run or replays a finished one as a terminal transcript; ora interactive --spec and ora local add a task picker and let you steer the running agent. Their pi-tui front end ships in ora-pi/ with the agent core, so the npm ci --prefix ora-pi above installs it. ora interactive without --spec shows a run in the Pi agent core's own terminal UI, which you can detach and re-attach (ora attach); it needs nothing beyond the agent core above. See run and inspect, interactive sessions and run ORA on your computer.

./scripts/ora play --env synthetic        # free play: a scene, no task, your instructions in turn
./scripts/ora web setup                   # once: build ORA's web page
./scripts/ora web RUN_ID                  # a live run's conversation and cameras in the browser
./scripts/ora replay RUN_ID               # a finished run on the same page at 16x (--export out.mp4: a video)

In free play the agent is Pi as a coding agent with the robot as its device: besides the robot tools it can script the robot in Pi's sandboxed codemode or with the ora-robot command, and the supervisor still executes every action. On a GPU server without a display, ora-remote runs the command over SSH and shows the terminal UI on your computer and the cameras, or ORA's web page, in your browser (remote GPU server).

Choose an environment

Environment Robot / simulator Guide
LIBERO / LIBERO-Pro Panda manipulation in MuJoCo Install and run
RoboTwin Dual-arm manipulation in SAPIEN Install and run
RoboDojo Isaac Sim task environments Install and run

The simulators, assets, perception weights, and GPU requirements are installed separately from ORA. Supported setups records the tested scope.

Find what you need

I want to… Read
Use a self-hosted model or Anthropic Model APIs
Store a key or add my own endpoint (ora providers) Keys in the terminal
Give the robot instructions myself, or script it Free play · Scripting the robot
Bring up, calibrate and recover a real robot cell (ora cell) Run a real robot cell
Run on a GPU server from my laptop, or watch in the browser Remote GPU server · Web view
Fix an installation or run problem Troubleshooting
Inspect a run or export evidence User guide
Understand the action and trust boundaries Runtime lifecycle
Configure a benchmark task Configuration
Run the official suites on a cluster Official suites · Evaluation protocol
Train a model on ORA's episodes Connect a training loop
Find where something lives in the source Architecture · Code map · Repository structure
Change tools or robot instructions Tool surfaces · Prompt bundles
Add a simulator Add an environment · Environment compatibility
Contribute or maintain these docs Start contributing · Contributing · Documentation guide