File queued to print
The safety check starts before the job reaches the fabrication controller.
print_job.3mf
Guard the boundary of 3D printing.
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
Local screening, not central surveillance
Geometry over guesswork
01 Explore
The classifier, and the laws that call for it.
Classifier
PrintGuard v1
How the classifier screens 3D-printing files for firearm components, and how it performs on a held-out benchmark.
- Firearm detection
- 96.75%
- False-positive rate
- 0.06%
3D-printed firearm laws
California AB 2047 and New York’s 2026 budget law put 3D-printer blocking on a timeline. Follow every tracked state on one map.
- Print-blocking laws
- 2
- States tracked
- 15
02 Where it fits
One safety layer. Many points of integration.
01
3D-printer manufacturers
Evaluate product-level safeguards against emerging performance requirements.
Email 02Slicing software & marketplaces
Screen files before slicing or publication, close to the existing workflow.
Email 03Labs & fabrication
Job-level intake controls for universities, makerspaces, and enterprise teams.
Email 04Public-safety partners
Support consistent file review while limiting unnecessary redistribution of sensitive CAD files.
Email03 In the public record
Reporting on the risk and the response.
Independent coverage of untraceable firearms, the rise of 3D-printed weapons, and emerging policy responses.
Associated Press · June 13, 2026
Some people are making guns with 3D printers. A new law seeks to cancel their print jobs.
Reporting on New York’s first-of-its-kind requirement, the technical questions it raises, and the emerging standards debate.
Read the report Opens in a new tab Associated Press · October 16, 2025Gun safety advocates warn of a surge in untraceable 3D-printed weapons in the US.
A look at recoveries reported by roughly two dozen police departments, cheaper fabrication tools, and concern about a new wave of homemade weapons.
Read the report Opens in a new tab Capitol News Illinois via NPR Illinois · June 12, 2026Southern Illinois man convicted in federal case involving 3D-printed guns.
Reporting on a federal conviction and the enforcement challenges surrounding increasingly sophisticated home gun-making.
Read the report Opens in a new tab NJ Spotlight News / PBS · April 16, 2024“Ghost guns” in NJ: Easy, cheap and deadly.
Statehouse reporting on crime-gun recoveries, 3D printing, conversion devices, and pressure on existing statutes.
Watch the report Opens in a new tabA practical middle path
Make 3D printing safer.
Keep innovation open.
We are building a practical screening layer for additive-manufacturing workflows—designed to reduce risk without adding unnecessary friction for lawful use.
Classifier
PrintGuard v1
A geometry classifier that screens 3D-printing files for firearm components before they are published, sliced, or printed. It reads the shape of the mesh rather than the filename, and keeps an auditable record of every decision.
- Firearm detection
- 96.75%
- False-positive rate
- 0.06%
- Per-file scoring
- <1 sec
- Held-out test files
- 10,000
01 The system
A software safety layer between every file and the printer.
PrintGuard can run as a cloud service called through an API or directly on printer hardware. Either way, the same classifier screens each file before fabrication and only releases jobs that clear the configured firearm-part policy.
PG / DEPLOYMENT PATH
Screening gate · before motion
02 / Choose deployment
Call through the API
Slicers, marketplaces, and print services send the file to a managed screening endpoint.
POST /v1/classify
Run on printer hardware
The classifier executes on the printer or local controller without sending the file to the cloud.
LOCAL / NO UPLOAD
Check for firearm-part risk
The classifier reads the shape itself—not the filename—and scores the file before any print motion is authorized.
MeshPointsVoxelsViews
04 / Enforce before print
Release to printer
The job continues only after it clears the active classification and policy line.
Apply configured action
Hold, block, or route according to jurisdiction-specific rules and workflow.
Hardened file intake
Bounded parsers validate STL, OBJ, AMF, 3MF, and OFF files before analysis.
Geometry, not filenames
Mesh statistics, point clouds, voxel occupancy, and multiview projections capture the durable shape signal.
Auditable policy action
Scores, evidence, thresholds, and the resulting pre-print action are retained in a decision record.
02 The gap
A geometry problem cannot be solved by a list of names.
Filenames are fragile
Names can be changed in seconds. Keyword filters confuse intent with a label.
Hashes only match exact files
A small file edit produces a new hash, even when the underlying geometry is effectively unchanged.
Geometry is the durable signal
PrintGuard extracts mesh statistics, sampled points, voxel occupancy, and multiview projections from the file itself.
03 Benchmark snapshot
Safety that works at the speed of a workflow.
A source-separated test set of firearm designs, firearm-specific parts, dual-use parts, near-firearm duplicates, and benign 3D files.
Percentage of firearm files successfully flagged.
Benign files incorrectly flagged. Lower means less friction for lawful use.
Per file, for average file sizes.
Source-separated test set.
V1 benchmark · July 2026
04 Built to be credible
Evidence before enforcement.
PrintGuard is built around documented datasets, source-separated testing, clear audit records, and human review.
mesh rows in the binary training manifest
benign mechanical examples selected to challenge the classifier
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 create a reviewable record.
Human where it matters
Ambiguous and high-impact decisions can move into a review workflow.
Built to evolve
Models, benchmarks, and policy rules can be updated as evidence improves.
Evaluate PrintGuard v1
Put it in front of
your file pipeline.
We work with printer makers, slicers, marketplaces, and print services to test PrintGuard on their own files and workflows.