Skip to content
NewMS Lattice found both sealed targets blind, in 32 minutes, for under 20 cents.See the proof →
Advancing Bits to Master Atoms
An ordered cubic crystal lattice of matte graphite, satin silver and cobalt-blue spheres connected by titanium rods on the right, aligned with a neat geometric grid of round silver and blue dots on the left.An ordered cubic crystal lattice of matte graphite, satin silver and cobalt-blue spheres connected by titanium rods on the right, aligned with a neat geometric grid of round silver and blue dots on the left.

A breakthrough in materials discovery

Search in bits. Build in atoms.

Name what the material must do. MS Lattice builds the crystal.

We sealed the answers away and gave it nothing but the brief. It found both, down to the arrangement of their atoms. In 32 minutes. For under 20 cents.

A clean cobalt-blue connector line enters from the left and docks into a faceted polyhedral core built from interlocking crystal lattice planes of matte graphite, satin silver and cobalt-blue spheres.A clean cobalt-blue connector line enters from the left and docks into a faceted polyhedral core built from interlocking crystal lattice planes of matte graphite, satin silver and cobalt-blue spheres.

Your AI agent just became a materials scientist.

MS Lattice is the engine. Your AI agent is the driver. Connect once and your agent can find, compute, verify and prove real materials. Without MS Lattice, an agent can talk about materials. With it, it can discover them.

tools, one connection
120
for an agent’s whole journey, from need to proof
5 min
Six distinct ordered crystal models of satin silver and cobalt-blue spheres stand on low matte graphite plinths in a gentle arc, each perfectly aligned beside its matching matte graphite twin.Six distinct ordered crystal models of satin silver and cobalt-blue spheres stand on low matte graphite plinths in a gentle arc, each perfectly aligned beside its matching matte graphite twin.

We hid the answer. MS Lattice found it anyway.

Two ultra-high-temperature ceramics, sealed away while it searched. Both found, down to the arrangement of their atoms. Four compounds it had never seen, CaO, SrF₂, BaTiO₃ and Ni₃Al, rebuilt to within a few hundredths of an ångström.

candidates
64
of compute
32 min
for the whole run
< $0.20
Close-up of a matte tungsten-carbide cutting-tool edge as a dense rock-salt crystal lattice of satin silver and cobalt-blue spheres locks cleanly along its surface.Close-up of a matte tungsten-carbide cutting-tool edge as a dense rock-salt crystal lattice of satin silver and cobalt-blue spheres locks cleanly along its surface.

You describe the job. MS Lattice names the material.

“A coating for dry, high-speed machining. 28 GPa. 800 °C in air. Under $30 a kilo.”

Back came (Ti,Al)N and (Cr,Al)N, the coatings the industry runs on today, in the top five. No starting structure. Just the job.

An ordered crystal of satin silver and cobalt-blue spheres rests squarely on a thin horizontal titanium datum plane, while dimmer matte graphite rival structures sit recessed below it.An ordered crystal of satin silver and cobalt-blue spheres rests squarely on a thin horizontal titanium datum plane, while dimmer matte graphite rival structures sit recessed below it.

Verified by first principles.

Stability against every rival phase, elastic constants and phonons, on call. What holds is confirmed. What does not is caught before the lab.

stability verdicts right
4 of 4
silicon reference values reproduced
5 of 5
On the left, a recessed blurred field of muted wireframe cubes; on the right in crisp focus, a neat row of five distinct crystals of matte graphite, satin silver and cobalt-blue spheres.On the left, a recessed blurred field of muted wireframe cubes; on the right in crisp focus, a neat row of five distinct crystals of matte graphite, satin silver and cobalt-blue spheres.

Hundreds of the right candidates, not millions of maybes.

Your requirements live inside the search. Proposals that break them are turned away before a structure is built, so compute goes only to contenders.

of compute per candidate
≈ $0.003

One sentence in. A shortlist out.

Five steps from your words to a ranked shortlist, with the proof attached. A miss stops on the spot.

Say what the material must do.

Step 1 of 5: Goal

Four modes. One engine.

One engine, four kinds of question: from a target with nothing to start from to a benchmark whose answers stay sealed.

What the engine sees
Your target, nothing more

Open Discovery

You give it
A domain, a goal preset or your own targets, and a budget.
It does
It searches the whole composition space.
You get
A ranked, diverse set of candidates, each with its record.

Best for: New materials, from the target alone.

Validation you can inspect.

A score is a claim. MS Lattice gives you the proof behind it: every candidate is judged in stages, and every check it passes stays on its record.

Step 1 of 5: Valid

The structure is valid.

Every verdict comes with its reasons.

Eleven material domains.

Batteries, magnets, coatings, catalysts, ceramics. Each domain speaks its own language of targets and limits. MS Lattice speaks all eleven.

  • Battery cathodes

    More energy, less cobalt.

    Layered NMC oxides · Layered NCA oxides · Spinel oxides · Polyanion frameworks · Sodium-ion layered oxides · Prussian blue analogues · Magnesium-ion spinels

  • Solid electrolytes

    Fast ions, in a stable solid.

    Garnets · NASICON-type conductors · Sulfides · Halides · Oxide-ion conductors · Proton conductors · Ceramic–polymer composites

  • Catalysis

    From single active sites to whole surfaces.

    Single-atom alloys · Alloy surfaces · Oxide-supported catalysts · Acid OER anodes · ORR alloys · CO₂ reduction surfaces

  • Magnets

    More field, fewer rare earths.

    High-performance NdFeB · Reduced-rare-earth NdFeB · Rare-earth-free MnAl · Hexaferrites · Iron–silicon · Iron–cobalt · Spinel ferrites

  • Photovoltaics

    Absorbers for the next solar cells.

    Halide perovskites · Double perovskites · Chalcohalides · Chalcogenide absorbers

  • Thermoelectrics

    Waste heat, put to work.

    Chalcogenides · Skutterudites · Half-Heuslers · Oxide thermoelectrics

  • High-entropy alloys

    Strength from many elements.

    Transition-metal alloys · Corrosion-resistant alloys · Lightweight alloys · Refractory alloys

  • Superconductors

    Five families, one search.

    Cuprates · Iron-based pnictides · Bilayer nickelates · MgB₂-type compounds · High-pressure hydrides

  • Thermal barrier coatings

    Hotter engines, protected parts.

    Stabilized zirconia · Rare-earth zirconates · High-entropy oxides · Environmental barrier coatings

  • Hard coatings

    Harder, hotter, longer-lasting.

    Nitrides and carbides · Diborides · MAX phases

  • Ultra-high-temperature ceramics

    For the hottest places in flight.

    Rock-salt carbides · Diboride composites · High-entropy carbides · High-entropy diborides

The usual pipeline, and MS Lattice.

Most AI discovery pipelines generate first and sort later. MS Lattice turns that around.

Your requirementsThe usual pipeline: Checked after generation, as a filterMS Lattice: Held inside the search, before a structure is built
What you getThe usual pipeline: Thousands to millions of structures to triageMS Lattice: Hundreds of ranked contenders, each with its record
PreferencesThe usual pipeline: Traded off by hand afterwardsMS Lattice: Pushed as far as they go, never at a must-have’s expense
The searchThe usual pipeline: A fixed model, run onceMS Lattice: Runtime intelligence that gets sharper with every evaluation
EvidenceThe usual pipeline: A score per structureMS Lattice: Every check on every candidate, rebuildable: 73 of 73

Two ways to work.

License MS Lattice for your own team and agents, or let Norck take your target all the way to a finished part.

  • License MS Lattice

    Your team. Your agents. Our engine.

    Every domain, every mode, from your own AI agent over MCP, the REST API, the Python SDK or the command line.

    License MS Lattice →
  • Discovery with Norck

    From a target to a finished part.

    Norck runs MS Lattice, then synthesizes, validates and manufactures the winner, all the way to your finished part.

    Discovery with Norck →

The latest from MatterSpace.

Launches, results and the ideas behind MS Lattice.

The first of our discovery engines.

MS Lattice is the first of MatterSpace’s discovery engines. More are on the way, for every problem in science and engineering whose space of possibilities is too large to search one try at a time.

Questions about MS Lattice.

Straight answers.

What is MS Lattice?

The materials discovery engine your AI agent drives. Name what the material must do. It finds the crystal, computes what it can do, verifies it with first-principles physics and proves it blind.

What does a campaign cost?

The blind benchmark ran 64 candidates for under 20 cents. About a third of a cent per candidate. You see the price before you pay it.

Can my own AI agent use it?

Yes. One connection, any model that speaks MCP.

How can we work with MatterSpace?

License MS Lattice, or let Norck take your target to finished parts. Norck runs MS Lattice under agreement with MatterSpace.

Stop guessing which crystal to make. Ask for it.

Tell us the domain and what the material must do. License MS Lattice for your team, or let Norck take the discovery all the way to finished parts.