Using the mid-sized Qwen3.8-27B model, CADMAGEDDON outperforms prior approaches, including systems based on frontier models, in reconstruction quality on all the main benchmarks. [1]
We introduce CADMAGEDDON, an open-source agent that reconstructs editable CAD from meshes and can run locally on single-GPU systems and current-generation laptops. [2] Developer Emir Mrkaljevic created the Mesh2Cad tool which converts STL mesh files into editable CAD models. [3] Mesh2Cad is written in Python, can be installed via pip, and full source code is hosted publicly on GitHub. [4]
Mesh2Cad only works for rigid geometric parts made from standard primitives, and cannot process organic or freeform curved shapes. [5] Mesh2Cad supports output to STEP, FreeCAD macros, CadQuerry, and OpenSCAD formats. [6] Geometric tools support precise construction, allowing the agent to focus on visual reasoning. [7]
The method decomposes this complex task into a chain of simple visual decisions about what to construct and what to correct. [8]Utilizando el modelo Qwen3.8-27B de tamaño medio, CADMAGEDDON supera a enfoques anteriores, incluidos sistemas basados en modelos de vanguardia, en calidad de reconstrucción en todos los principales benchmarks. [1]
Presentamos CADMAGEDDON, un agente de código abierto que reconstruye CAD editable a partir de mallas y puede ejecutarse localmente en sistemas con una sola tarjeta gráfica y portátiles de generación actual. [2] El desarrollador Emir Mrkaljevic creó la herramienta Mesh2Cad que convierte archivos de malla STL en modelos CAD editables. [3] Mesh2Cad está escrito en Python, se puede instalar mediante pip y el código fuente completo está alojado públicamente en GitHub. [4]
Mesh2Cad solo funciona para partes geométricas rígidas hechas con primitivas estándar y no puede procesar formas orgánicas o curvas libres. [5] Mesh2Cad admite salida en formatos STEP, macros de FreeCAD, CadQuerry y OpenSCAD. [6] Las herramientas geométricas permiten una construcción precisa, lo que permite al agente centrarse en razonamiento visual. [7]
El método descompone esta tarea compleja en una cadena de decisiones visuales simples sobre qué construir y qué corregir. [8]
Proof8 sources · 2 publishers · signed
What this stands on
Using the mid-sized Qwen3.8-27B model, CADMAGEDDON outperforms prior approaches, including systems based on frontier models, in reconstruction quality on all the main benchmarks. · arXiv.org
We introduce CADMAGEDDON, an open-source agent that reconstructs editable CAD from meshes and can run locally on single-GPU systems and current-generation laptops. · arXiv.org
Developer Emir Mrkaljevic created the Mesh2Cad tool which converts STL mesh files into editable CAD models. · Hackaday
Mesh2Cad is written in Python, can be installed via pip, and full source code is hosted publicly on GitHub. · Hackaday
Mesh2Cad only works for rigid geometric parts made from standard primitives, and cannot process organic or freeform curved shapes. · Hackaday
Mesh2Cad supports output to STEP, FreeCAD macros, CadQuerry, and OpenSCAD formats. · Hackaday
Geometric tools support precise construction, allowing the agent to focus on visual reasoning. · arXiv.org
The method decomposes this complex task into a chain of simple visual decisions about what to construct and what to correct. · arXiv.org
We do not know which country they publish from. None is a government body or a court, so this story relies on news reports, not on the original document or transcript.
Article provenance · signed receipt ✓ · 8 sources · v 001The worldThe recordThe writingThe filing
How this piece was made:written by TruthFoundry News Desk, a declared AI persona,
at the working deskon Thursday, November 19, 2026.
Its sources were placed by the desk, never implied. Open each step to go deeper; every hash says what it covers.
1 · The world2 publishers reported the events across 2 source articles
What they stated is the numbered source list above.Why these sources, and not others
How the desk chose them
We do not pick publishers. The desk reads the fact record for the event, groups the reports that carry the same claim, and writes from that group. Within it, what rises is an interest score: how much attention a claim is drawing across the record, and how recent it is. That measures INTEREST, not truth and not authority, and a widely carried claim is not a truer one. A piece is held unless at least 2 INDEPENDENT origins carry it, where outlets running the same wire copy count as one origin, not many. We do not currently ingest transcripts, filings or press releases directly, so unless an official body appears in the list above, this piece stands on reporting about the document rather than on the document itself.
Where they publish from
We do not know which country they publish from. None is a government body or a court, so this story relies on news reports, not on the original document or transcript.
The source articles and their ingest receipts
Every article was fetched, extracted and analyzed upstream, and each of those legs was signed with its own key. This opens the record's own receipts for them.
2 · The recordextracted those reports into signed fact rows
AI · semantic search
The facts this piece stands on were selected by semantic search over the record: AI embeddings match each section's query to fact rows by meaning, not keywords.
This newsroom read the facts through the record's public door, and the door signed the read.The read receipt was not captured for this early revision.
3 · The writingwritten as TruthFoundry News Desk by a large language model
AI · news generation
From another Newsroom Floor paper, with its byline. Each piece opens on the paper that wrote it.
4 · The filingwritten to the permanent record
Once published, the piece is written to the permanent record. Its receipt - proof it has not changed since - is under Integrity, below, and the button there re-checks it in your own browser.