Open Humanoid Engineering

Build intelligence from matter up.

An open, AI-native engineering school for building humanoids from chemistry to computation.

Read the manifesto Explore the curriculum
Exploded engineering schematic showing a complete humanoid and its mechanical assemblies
  1. Chemistry
  2. Materials
  3. Mechanics
  4. Electrical
  5. Computer Science

Biomechanics + Neuroengineering

Engineering has to become whole again.

Software made abstraction abundant. Artificial intelligence makes it nearly free. The next frontier is not another layer of abstraction—it is the difficult return to matter, energy, movement, uncertainty, and consequence.

  1. 01

    Matter before models.

    Intelligence begins with chemistry, surfaces, structures, friction, heat, and failure. A model is useful only when it remains accountable to the world it represents.

  2. 02

    Evidence before claims.

    Every design decision must point to an equation, a simulation, a test, and a stated limitation. Reproducibility is the native language of trust.

  3. 03

    AI as collaborator, never alibi.

    Students work with AI from day one. They also expose its assumptions, challenge its answers, inject faults, and remain responsible for the final engineering judgment.

  4. 04

    Open progress compounds.

    Laboratories, failures, evidence, and appeals belong in public. The school grows by making every verified contribution available to the next team.

One humanoid. Four years. Every course a project.

Each year deepens one layer while carrying every previous layer forward.

  1. 01

    Chemistry → Materials

    Intelligent limb

    Cells, surfaces, lubricants, polymers, metals, composites, fatigue, and a virtual human-scale joint grounded in anatomy.

  2. 02

    Mechanics

    Fixed-base upper body

    Actuators, transmissions, arms, hands, tribology, manufacturability, grasping, and tool use in a circular workcell.

  3. 03

    Electrical

    Walking full-body twin

    Drives, battery management, sensing, real-time networks, balance control, and functional safety under injected faults.

  4. 04

    Computer Science

    Autonomous digital humanoid

    Whole-body control, robot learning, VLA systems, planning, cybersecurity, human intervention, and trustworthy autonomy.

Continuous human reference Biomechanics + Neuroengineering runs through every year: anatomy, movement, motor control, ergonomics, injury limits, and human–robot interaction.

The laboratory is software.

Students reproduce, explain, extend, challenge, and publish AI-generated laboratories with their own AI agents.

  1. Reproduce
  2. Explain
  3. Extend
  4. Challenge
  5. Publish
01

AI Lab Package

manifest.yaml
models/
instruments/
faults/
evidence.schema.json

Versioned physics, instruments, data, fault scenarios, and protected tests.

02

Project Workspace

Shared CAD, code, models, runs, decisions, and transparent AI provenance.

03

Evidence Graph

Every claim remains connected to its model, run, metric, and known limit.

04

AI Jury Report

PASS / CONTESTED

Independent domain agents publish reasoning, confidence, and dissent.

05

Open Appeal

FAULT_INJECTION_07

Anyone can submit reproducible counter-evidence to a fresh, blind AI jury.

Specialize at the intersections.

After four shared years, a fifth-year frontier portfolio turns breadth into a precise research direction.

  1. 01

    Computational Chemistry, Energy & Interfaces

  2. 02

    AI-Designed Materials & Soft Robotics

  3. 03

    Humanoid Mechanics & Dexterous Manipulation

  4. 04

    Intelligent Power, Actuation & Edge Systems

  5. 05

    Embodied AI & Robot Learning

  6. 06

    Neuroengineering & Human–Robot Symbiosis

  7. 07

    Trustworthy Digital Twins & Autonomous Circular Manufacturing

YEAR 04 Integrated Humanoid Engineering Portfolio
YEAR 05 Advanced Open Engineering Portfolio

If it survives the digital world, it earns the chance to enter the physical one.

A design that survives multi-physics simulation, randomized environments, injected failures, energy and thermal limits, cyberattacks, and unseen tasks may be designated a Production Candidate.

That designation does not certify a physical robot. It means the evidence is strong enough to seek funding, manufacturing review, and independent physical validation.

Read on GitHub