# ALOHA

Repository: https://github.com/tonyzhaozh/aloha
Canonical: https://ross.abutalabs.com/products/aloha
Language: Python
License: MIT
License Family: permissive
Last push: 2024-04-19T22:20:33+00:00

## Health v2 (maintenance only)
Score: 31/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 92
- inputs: {"age_days": 1288, "days_push": 866, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2310, forks 337 (observed 2026-08-28T04:06:36.043048+00:00)

## What it is
ALOHA is an open-source hardware and software system for low-cost bimanual robot teleoperation and demonstration data collection, built on ROS and Interbotix robot arms. It pairs with the ACT repository for training imitation learning policies from the collected teleoperation data.

## Use cases
- collect robot manipulation demonstrations via teleoperation
- train imitation learning policies for bimanual robot arms
- set up a low-cost dual-arm robot teleoperation rig
- stream camera and robot joint data over ROS
- record teleoperated episodes for behavior cloning

## When to choose
- you are building or replicating the ALOHA bimanual robot hardware
- you need to collect teleoperation demonstrations for imitation learning
- you want an open-source alternative to expensive commercial teleoperation systems
- you are training ACT or similar behavior-cloning policies

## When to avoid
- you need a simulation-only robotics environment without real hardware
- you are not using ROS 1 with Interbotix ViperX arms
- you need a plug-and-play commercial robot solution with support
- you work on Windows or macOS since only Ubuntu + ROS noetic is tested

## Facets
- artifact type: application
- maturity: active
- function: robotics, simulation, machine-learning, data-science
- domain: robotics, machine-learning, hardware
- platform: python
- tags: teleoperation, bimanual-manipulation, imitation-learning, ros, robot-arms, data-collection, act, linux

## Member repositories
- tonyzhaozh/aloha (main) score 31
- tonyzhaozh/act (backend) score 31

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:36.043048+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:39:33.252916+00:00, confidence not recorded.
  - readme: https://github.com/tonyzhaozh/aloha (fetched 2026-08-28T04:06:36.043048+00:00, sha 803e7dff2e06)
- Data as of 2026-08-30T08:39:29.467469+00:00.