AgentsModelsSkillsMemoryBotsStack FinderEvaluationsGuidesSubmit a resource
Apache-2.0 · Bots

AIRA

3D-printable 7-DoF robotic arm with native LeRobot integration for ACT, Diffusion, PI0, and GR00T.

GitHub Open repository
0.2K stars 0.0K forks Apache-2.0 license 2026-06-04 verified
bash
$git clone https://github.com/robertorobotics/Nextis-AIRA-3D && cd Nextis-AIRA-3D && pip install -e .
Open sourceSelf-hosted
Overview

What is AIRA?

AIRA is a fully 3D-printable, 7-degree-of-freedom (6-DoF + 1-DoF gripper) robotic arm designed as a native LeRobot plugin. It plugs directly into the LeRobot ecosystem — ACT, Diffusion Policy, PI0, GR00T N1.5, and every other policy in the LeRobot framework work out of the box. With an interactive setup wizard, Damiao CAN bus motors, and MIT impedance control, AIRA is designed for makers, researchers, and educators who want an open, affordable platform for robot learning.

LeRobot-native plugin architecture

AIRA registers with LeRobot's plugin system — install via pip, and LeRobot discovers the robot and teleoperator automatically. Not a fork, so updates come from upstream LeRobot.

You get the latest LeRobot features and policies without maintaining a separate fork. Install, plug in, and train.

3D-printable and open hardware

The full frame is 3D-printable, with STEP files, STLs, and assembly guides available. Verified kit and CNC aluminum upgrade options also available.

Hardware cost has been the main barrier to entry in robotics research. 3D printing brings the cost down by an order of magnitude.

Damiao CAN bus motors with MIT impedance control

High-torque CAN bus motors (base joints at 20/35 Nm) with compliant impedance control for safe, smooth teleoperation and policy deployment.

CAN bus motors provide the torque and precision needed for real manipulation tasks, while impedance control ensures safe human-robot interaction.

Interactive setup wizard

The aira-setup wizard guides users through motor-by-motor configuration with no terminal expertise needed.

Setting up a robotic arm typically requires deep embedded systems knowledge. AIRA's wizard makes it accessible to ML researchers.
Install

One command to start

$ git clone https://github.com/robertorobotics/Nextis-AIRA-3D && cd Nextis-AIRA-3D && pip install -e .
Use cases

What teams use it for

Affordable robot learning platform for education

Print and assemble an AIRA arm in a university lab, install LeRobot, and have students go from teleoperation to policy training in a single semester.

VLA policy prototyping before industrial deployment

Prototype manipulation policies on AIRA, validate with real-world data, then transfer to production hardware using the same LeRobot codebase.

Open-source teleoperation data collection

Use AIRA's leader-follower setup with MIT impedance control to collect high-quality demonstration data for training imitation learning policies.

Ecosystem

Tags & capabilities

botopen sourceroboticsmessagingopen sourceself hosted
Comparison

How it stacks up

Choose AIRA for open, affordable LeRobot-native hardware

vs SO-100 / SO-101 arms

SO-100 arms are cheaper but have fewer degrees of freedom. AIRA's 7-DoF, CAN bus motors, and LeRobot plugin architecture make it more capable and easier to integrate.

FAQ

Questions

Do I need a 3D printer to build AIRA?

No. You can print the frame yourself, order a verified kit, or upgrade to CNC aluminum. All options are documented.

What policies can I run on AIRA?

Any LeRobot-compatible policy: ACT, Diffusion, VQ-BeT, PI0, PI0.5, GR00T N1.5, SmolVLA, XVLA, and more. No code changes needed.

Does AIRA support bimanual (dual-arm) setups?

The current release focuses on single-arm setup. Bimanual support may be added in future releases based on community interest.

Decision brief

Should you use AIRA?

JSON
Best for
  • Makers and educators building an affordable robot learning platform
  • Researchers wanting a LeRobot-compatible arm without the Franka price tag
  • Teams prototyping manipulation policies before scaling to industrial hardware
Not for
  • Industrial precision manufacturing (3D-printed frame has lower stiffness than CNC aluminum)
  • Teams needing a turnkey robot without any assembly or tuning
Trust and freshness
  • Verified 2026-06-04
  • License: Apache-2.0
  • Repo: robertorobotics/Nextis-AIRA-3D
  • Open-source signal
Deployment

self hosted, cloud

Permission surface

messages, hardware

Decision signals

Self-hostable

Agent packet

Structured decision data for AIRA

This packet is the compact machine-readable view agents should use before following source links or taking action.

Full JSON Agent packet Markdown brief
Capabilities

robotics, messaging

Constraints

open source, self hosted

Deployment

self hosted, cloud

Permission surface

messages, hardware

Recommended workflows

Browser automation, Connector or protocol layer, Robotics or embodied agent workflow

Overview

What AIRA does

What it is

AIRA is a 7-DoF (6-DoF arm + 1-DoF gripper) robotic arm that connects to LeRobot via its plugin system. It uses Damiao CAN bus motors with MIT impedance control for safe, smooth teleoperation. The complete hardware design — STEP files, STLs, mechanical drawings, and PCB files — is open source. The software registers with LeRobot automatically via Python packaging conventions, so any LeRobot policy (ACT, Diffusion, PI0, GR00T) works without code changes.

Why it matters

The robotics field has a hardware access problem. Quality research-grade arms cost $10,000-$50,000. Hobbyist arms lack the precision and software ecosystem needed for serious robot learning. AIRA fills the gap: it is affordable enough for individual researchers and educators, but its LeRobot-native design means it runs the same state-of-the-art VLA policies as a Franka arm.

How to evaluate it

AIRA registers with LeRobot's pkgutil-based plugin discovery system. When you run lerobot-teleoperate --robot.type=aira_follower, LeRobot finds lerobot_robot_aira and lerobot_teleoperator_aira automatically. The leader arm uses LeRobot's built-in Dynamixel driver, while the follower uses AIRA's custom Damiao CAN bus driver. MIT impedance control provides compliant position tracking on the follower for smooth teleoperation.

Facts

Known metadata and operating surface

These fields are separated from editorial interpretation so agents can reason over facts and missing checks.

Resource type bot
Category Bots
Maturity active
Difficulty Unknown
License Apache-2.0
Pricing open source
Verified 2026-06-04
Source confidence high
Risk level elevated
Fit matrix

Where AIRA fits in an agent stack

strong

Browser automation

AIRA has multiple signals for browser automation, including matching tags, capabilities, category, or positioning.

  • Run one non-sensitive website task and inspect clicks, waits, retries, and changed URLs.
  • Confirm official docs, current maintenance, license, and runtime constraints before production use.
strong

Connector or protocol layer

AIRA has multiple signals for connector or protocol layer, including matching tags, capabilities, category, or positioning.

  • Connect one low-risk service, then inspect schemas, auth scope, errors, and logs.
  • Confirm official docs, current maintenance, license, and runtime constraints before production use.
strong

Robotics or embodied agent workflow

AIRA has multiple signals for robotics or embodied agent workflow, including matching tags, capabilities, category, or positioning.

  • Separate simulator claims from hardware claims and verify safety boundaries before real-world operation.
  • Confirm official docs, current maintenance, license, and runtime constraints before production use.
partial

Coding agent workflow

AIRA has at least one signal for coding agent workflow, but should be checked against a real task before adoption.

  • Run a small repository change and inspect the diff, tests, and rollback path.
  • Confirm official docs, current maintenance, license, and runtime constraints before production use.
partial

Local or private AI stack

AIRA has at least one signal for local or private ai stack, but should be checked against a real task before adoption.

  • Verify hardware requirements, data path, storage, and whether all calls stay in your environment.
  • Confirm official docs, current maintenance, license, and runtime constraints before production use.
weak

Evaluation and observability

AIRA is not primarily positioned for evaluation and observability in the current metadata.

  • Add one repeatable test case and confirm results can run again in review or CI.
  • Confirm official docs, current maintenance, license, and runtime constraints before production use.
Inputs and outputs

What an agent should inspect

Likely inputs

  • Repositories, files, issues, terminal output, and test results
  • Official setup instructions and a small real workflow

Likely outputs

  • Diffs, commits, explanations, test results, or review notes
  • A decision on whether this resource fits the target workflow
Evidence

Sources, claims, and missing checks

Claims are marked separately from source links so future crawlers and reviewers can update them without rewriting the page.

GitHub github

Repository source for code, license, issues, releases, and implementation details.

 Homepage homepage

Official or project-controlled source for this resource profile.
verified

AIRA is listed as open source.

License metadata: Apache-2.0
verified

AIRA has a recorded GitHub repository: robertorobotics/Nextis-AIRA-3D.

Resource facts and GitHub source link.
inferred

AIRA supports these recorded deployment modes: self hosted, cloud.

OpenAgent decision signal metadata.
inferred

AIRA is tagged with robotics, messaging capabilities.

OpenAgent capability taxonomy.
Missing checks
  • Dedicated docs link is missing.
  • Repository freshness has not been recorded.
Next action

How to start evaluating AIRA

Inspect repository

Check license, recent activity, issues, examples, and security-sensitive code paths.

Open source

Open Homepage

Start from the official source before adopting third-party instructions.

Open source

Install AIRA plugin

Clone and install the AIRA LeRobot plugin.

git clone https://github.com/robertorobotics/Nextis-AIRA-3D && cd Nextis-AIRA-3D && pip install -e .
Compare

Alternatives and nearby resources

Use related resources to compare category fit, license, deployment model, and first-workflow behavior.

Wegent

Open-source AI-native operating system for defining, organizing, and running intelligent agent teams.

Bots Dograh

Open-source self-hosted voice AI platform with visual workflows, MCP support, BYOK model routing, and telephony.

Bots Tiledesk

Open-source customer support and AI agent builder with human-in-the-loop workflows.

Bots
FAQ

Common questions about AIRA

Do I need a 3D printer to build AIRA?

No. You can print the frame yourself, order a verified kit, or upgrade to CNC aluminum. All options are documented.

What policies can I run on AIRA?

Any LeRobot-compatible policy: ACT, Diffusion, VQ-BeT, PI0, PI0.5, GR00T N1.5, SmolVLA, XVLA, and more. No code changes needed.

Does AIRA support bimanual (dual-arm) setups?

The current release focuses on single-arm setup. Bimanual support may be added in future releases based on community interest.