Defensive infrastructure for additive manufacturing

Keep the promise of
3D printing.
Guard the boundary.

PrintGuard identifies firearm-related risk before a file is published, queued, or fabricated—locally, quickly, and with an auditable record.

Local screening Auditable decisions Practical compliance Scroll to explore

Additive manufacturing is becoming ordinary infrastructure.

Schools, labs, manufacturers, marketplaces, makerspaces, and homes are gaining extraordinary new creative capacity. The same accessibility also opens a public-safety gap: restricted components can move from digital file to physical object outside traditional compliance checkpoints.

Policy is moving toward performance-based safeguards. The market needs a standard that reduces risk, withstands public scrutiny, and protects lawful making.

A geometry problem cannot be solved by a list of names.

A

Filenames are fragile

Names can be changed in seconds. Keyword filters confuse intent with a label.

B

Hashes are brittle

Small file edits break static matches, even when the underlying geometry remains recognizable.

C

Shape is the evidence

PrintGuard reads the file itself—its mesh, point cloud, volume, views, and known geometry.

A fast first line of review, built for the real world.

PrintGuard combines known-file evidence with shape-aware classification, then turns the result into a decision an organization can inspect and defend.

  1. 01

    Accept

    Screen common mesh formats at the point of publication, intake, or print.

  2. 02

    Understand

    Extract mesh statistics, point-cloud, voxel, and multiview features.

  3. 03

    Compare

    Check exact SHA-256 evidence, near-geometry matches, and classifier scores.

  4. 04

    Route

    Return a decision and confidence, then preserve the evidence for review.

PG / ANALYSIS CORE Local process
XYZ
FILEmesh.stl
STATEINGESTING
ROUTEREVIEW LAYER
Accepting fileNative, local mesh parser
STLOBJAMF3MFOFF STEP / STP routed for conversion

Safety that works at the speed of a workflow.

A source-separated test set spanning firearm, dual-use, near-firearm, and benign files.

Firearm detection 0%

Percentage of firearm-related files successfully flagged.

False-positive rate 0%

Benign files incorrectly flagged. Lower means less friction for lawful use.

Average scoring <0 sec

Per file, for average file sizes.

Held-out evaluation 0 files

Source-separated test set.

V1 benchmark · July 2026 These figures reproduce the current PrintGuard brief and will evolve with continued independent testing.

Evidence before enforcement.

A safety control only earns trust when it can explain itself, protect lawful users, and improve under scrutiny. PrintGuard is designed around manifested data, auditable labels, source-separated evaluation, and human review.

01 / Training foundation113,368

mesh rows in the binary training manifest

02 / Lawful lookalikes99,848

hard-negative mechanical examples

03 / Restricted evidence13,520

positive mesh examples from authorized channels

Local-first

Screening can happen where files already live, without centralizing every design.

Auditable by design

Hashes, model scores, evidence, and decisions form a reproducible record.

Human where it matters

Ambiguous and high-impact decisions can move into a review workflow.

Designed to improve

Regular model, benchmark, and policy updates are part of the system—not an afterthought.

Help define what good looks like.

PrintGuard is seeking pilot partners, public-sector sponsors, technical reviewers, and investment support to help establish a practical reference implementation for emerging performance standards.

California AB 2047 contemplates detection performance standards, benchmark datasets, and regular updates. New York has moved toward blocking-technology requirements. Comparable frameworks are emerging elsewhere.

The durable answer will require manufacturers, researchers, public institutions, and policymakers to build it together.

A national question, moving state by state.

PrintGuard tracks 2025–26 measures that expressly address printer blocking, 3D firearm manufacture, digital instructions, or serialization, alongside operative precursor laws cited by those measures.

Enacted Active Introduced Concluded

Scope: 2025–26 state measures expressly addressing printer blocking, 3D firearm manufacture, digital instructions, or serialization, plus operative precursor laws already cited by those measures. This focused tracker does not attempt to catalog every general firearm or ghost-gun bill. It is informational, may not be exhaustive, and is not legal advice. Statuses last reviewed July 17, 2026.

A practical middle path

Make 3D printing safer.
Keep innovation open.

We are building the compliance boundary that regulated production needs—without making lawful creation harder than it needs to be.