# enactic/openarm

A fully open-source humanoid arm for physical AI research and deployment in contact-rich environments.

Repository: https://github.com/enactic/openarm
Canonical: https://ross.abutalabs.com/products/openarm
Homepage: https://openarm.dev
Language: MDX
License: Apache-2.0
License Family: permissive
Topics: bilateral-teleoperation, genesis, humanoid-robot, imitation-learning, machine-learning, open-source, python, reinforcement-learning, robot, robot-arm, robotics, ros2, teleoperation, openarm, force-feedback, gravity-compensation, moveit2, mujoco
Last push: 2026-08-20T00:24:40+00:00

## Health v2 (maintenance only)
Score: 69/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 98, release rhythm 42, longevity 50
- inputs: {"age_days": 703, "days_push": 14, "days_rel": 306, "gap_med": 43, "n_releases_24m": 4}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2889, forks 319 (observed 2026-08-28T04:07:28.256194+00:00)

## What it is
OpenArm is a fully open-source 7DOF humanoid robot arm (hardware, firmware, and software) designed for physical AI research and deployment in contact-rich environments. It supports teleoperation with bilateral force feedback, imitation learning, simulation, and reproducible real-world data collection via a standardized evaluation cell.

## Use cases
- collect teleoperation data for imitation learning
- train RL policies on a real robot arm
- run reproducible physical AI benchmarks
- build an affordable bimanual humanoid research platform
- simulate a humanoid arm in MuJoCo or Genesis
- control robot arm motors over CAN

## When to choose
- you need an affordable, fully open-source robot arm for physical AI research
- you want safe human-robot interaction with compliant, backdrivable joints
- you need bilateral force feedback for contact-rich teleoperation
- you want reproducible evaluation conditions across labs

## When to avoid
- you need an industrial high-payload manipulator
- you want a turnkey commercial robot with vendor support
- you are not comfortable assembling or sourcing hardware components

## Facets
- artifact type: application
- maturity: active
- function: robotics, simulation, machine-learning, reinforcement-learning, sdk
- domain: robotics, machine-learning, hardware, simulation
- platform: python, cpp
- tags: humanoid-robot, robot-arm, teleoperation, imitation-learning, force-feedback, ros2, mujoco, open-hardware, physical-ai, bimanual, linux

## Member repositories
- enactic/openarm (main) score 69

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:28.256194+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 2026-08-30T07:35:21.135058+00:00, confidence not recorded.
  - readme: https://github.com/enactic/openarm (fetched 2026-08-28T04:07:28.256194+00:00, sha b0fce07f497c)
  - homepage: https://openarm.dev (fetched 2026-08-29T09:50:53.430176+00:00, sha 9d4f4bfb80c8)
  - site_page: https://docs.openarm.dev (fetched 2026-08-29T09:50:53.439915+00:00, sha 582ce56dd428)
- Data as of 2026-08-30T08:39:29.467469+00:00.