Skip to main content

Universal Generation Engine

MatterSpace
The Universal Generation Engine.

Your agents define constraints. The engine generates candidates valid by construction. Materials, drugs, chips, algorithms, biology — one engine, domain packs per field. Agent-first from the ground up.

Multi-objective Pareto optimization. Adaptive dynamics. Deterministic replay. Built from first principles — not a wrapper around diffusion models or RL. Designed for your agents.

The Problem

Generate-then-filter is not generation.

RL, autoregressive, and diffusion models optimize the wrong objective and produce the wrong artifacts. Post-hoc filtering is expensive screening, not discovery.

No Physics Grounding

RL treats molecular structures as token sequences or point clouds. It has no concept of energy landscapes, symmetry groups, or physical constraints. Outputs are statistically plausible, not physically valid.

No Constraint Enforcement

Autoregressive models generate one token at a time. Physical constraints — bond lengths, coordination numbers, charge neutrality — cannot be enforced during generation. They are applied as post-hoc filters that discard most candidates.

No Diversity Guarantee

RL collapses to reward-maximizing modes. It returns one answer, not a landscape of alternatives. Scientific discovery requires exploring the Pareto front across competing objectives.

No Provenance

Neither RL nor autoregressive models produce deterministic replay recipes, constraint satisfaction records, or typed artifacts. Results cannot be audited, reproduced, or composed across teams.

The Engine Family

One engine. Every domain. Domain packs per field.

MatterSpace is a universal generation engine built from the ground up on first principles. The core engine navigates learned energy landscapes with an adaptive dynamics controller. Domain packs supply the physics, constraints, objectives, and samplers for each field. One engine. Every domain. MatterSpace is patent pending in the United States and other countries.

MatterSpace Lattice

Materials Discovery Engine

Crystal structures, alloys, coatings, electrolytes, superconductors, photovoltaics, thermoelectrics, catalysts, magnets, and high-entropy alloys. 9 domain packs. Ready.

Ready

MatterSpace Pharma

Drug Discovery Engine

Molecular generation guided by binding energy landscapes. Constraint-aware synthesis ensures drug-likeness, solubility, and ADMET compliance. Target-aware, physics-grounded candidate design.

Early Testing

MatterSpace Algo

Algorithm Discovery Engine

Matrix n-rank algorithm search and computational optimization. Discovers novel algorithmic structures by navigating solution landscapes under complexity and correctness constraints.

Early Testing

MatterSpace Tessera

Chip Design Engine

Semiconductor architecture, photonic layout, and circuit topology optimization. Navigates design-rule landscapes to generate physically valid, manufacturable configurations.

Early Testing

MatterSpace Longevity

Epigenetic Reprogramming Engine

Partial epigenetic reprogramming target discovery. Navigates the Yamanaka factor landscape to identify safe, reversible rejuvenation interventions grounded in cellular biology constraints.

Early Testing

Architecture

Same structure. Different science. One engine.

Vareon builds universal discovery and generation engines from the ground up on first principles for your agents. Our AI agent teams design, implement, and validate these engines using patent-pending methods that fuse generative AI, physics-inspired generation, and control systems theory.

The insight behind MatterSpace is structural: every scientific discovery problem — whether in materials, pharmaceuticals, semiconductors, or biology — shares the same computational architecture. A high-dimensional landscape governed by physical laws. Constraints that define what is valid. A search for optimal configurations across competing objectives. A need for diverse, physically valid candidates, not a single reward-maximizing answer. If the computational structure is the same, the engine can be the same. What changes is the science — and that is what domain packs encode.

Separate the engine from the science

MatterSpace separates the domain-agnostic engine from domain-specific science. The engine navigates learned energy landscapes with an adaptive dynamics controller that switches between four physics modes in real time. It enforces constraints during generation, not after. It explores multi-objective Pareto fronts instead of collapsing to single optima.

Domain packs supply everything the engine cannot infer on its own: the force fields, physical constraints, symmetry groups, objective functions, compositional samplers, and validation criteria specific to each scientific domain. New domains require new packs — not new engines, not new architectures, not new fundamental research.

This separation is why MatterSpace Lattice can discover catalysts today, and the same engine architecture will generate drug candidates, semiconductor materials, and biological constructs tomorrow. The engine is the constant. The science is the variable.

Core Engine

Domain-agnostic — the same across every field

  • Learned energy landscape navigation
  • Adaptive dynamics controller with real-time mode switching
  • Constraint enforcement during generation, not post-hoc
  • Multi-objective evolutionary optimization across Pareto fronts
  • Deterministic replay, provenance, and evidence ledger

Domain Pack

Field-specific — swapped per scientific domain

  • Force fields and energy models calibrated to the domain
  • Physical constraints (symmetry, bonds, charges, stoichiometry)
  • Objective functions and multi-criteria scoring
  • Compositional and structural samplers
  • Validation tiers, acceptance criteria, and blind benchmarks

Generative AI

The engine learns to generate candidate structures in continuous configuration space. Not sequence-to-sequence prediction. Not autoregressive token generation. Learned energy landscape traversal that produces valid structures by navigating physics, not by sampling from a language model.

Physics-Inspired Generation

Candidates are generated through dynamics that respect the physical laws of the target domain. Energy conservation, symmetry invariance, and constraint satisfaction are properties of the generation process itself. Every output is valid by construction, eliminating post-hoc filtering entirely.

Control Systems Theory

The adaptive dynamics controller treats generation as a control problem. Four modes are selected in real time based on landscape conditions and exploration history. The controller, not the user, decides how to explore.

MatterSpace is patent pending in the United States and other countries. Vareon, Inc.

Adaptive Dynamics

Four modes. One controller. Real-time switching.

The adaptive dynamics controller switches between four physics modes at every step based on gradient state and exploration history. Not a schedule. Real-time adaptation to the energy landscape.

Local Refinement

Focused refinement toward nearby stable configurations. The baseline for improving candidate geometries and finding stable structures from an initial starting point.

Stochastic Exploration

Controlled randomness balanced with directional progress. Escapes shallow local minima and explores the surrounding energy landscape without abandoning physical plausibility.

Barrier Crossing

Controlled transitions that traverse energy barriers insurmountable through gradual exploration alone. Reaches globally optimal configurations in complex, multi-basin landscapes.

Rapid Stabilization

Locks the system into a physically valid configuration with decaying intensity. Ensures the final structure satisfies all domain constraints and is realizable for synthesis or further analysis.

Campaign Modes

Four ways to discover

Each campaign mode represents a different relationship between the engine and known science. From pure greenfield exploration to the strictest blind benchmark, agents select the mode that matches their intent.

Greenfield

Open Discovery

Greenfield exploration. No reference structure, no target. MatterSpace searches the full compositional and structural landscape under physics constraints. Pure discovery.

Refinement

Prototype Optimization

Start from a known structure and explore its local neighborhood. Refine compositions, geometries, and properties while staying within the stability basin of the anchor.

Validation

Guided Rediscovery

Target structures inform the search. Similarity scoring weights guide generation toward known configurations. Useful for validating the engine against established science.

Benchmark

Blind Rediscovery Benchmark

The strictest mode. Targets are evaluation-only — completely hidden from the generation pipeline. Zero information leakage. The north star benchmark for engine capability.

The Pipeline

From target to archive

Define what you want. MatterSpace selects from hundreds of parameters, picks the best pipeline, and runs it. Every step is observable. Nothing is a black box.

01

Define

Agent or human specifies target properties, constraints, and objectives. MatterSpace auto-selects the domain pack, dynamics parameters, and campaign mode.

02

Generate

Candidate structures are sampled from the domain-specific compositional and structural search space. Initial configurations respect symmetry and stoichiometry constraints.

03

Navigate

The adaptive dynamics controller drives candidates through the energy landscape. Four modes fire in real time based on gradient state and exploration history.

04

Enforce

Physical constraints are enforced during navigation, not after. Bond lengths, coordination numbers, symmetry groups, charge neutrality — validated at every step.

05

Validate

Multi-tier validation. Fast filters eliminate non-viable candidates. Relaxation confirms local stability. Property prediction scores against objectives. High-fidelity verification on top candidates.

06

Score

Multi-objective scoring across competing properties. Not a single best answer — a diverse archive of Pareto-optimal candidates trading off real-world constraints.

07

Archive

Every candidate is a typed, provenanced artifact. Full configuration snapshots, dynamics trajectories, constraint satisfaction records, and deterministic replay recipes.

AI-Native Architecture

Your agents. Our engine. One API.

MatterSpace is designed for AI agents as the primary user. Human accessibility is a feature, not the architecture. Every surface is machine-readable, every artifact is typed, every campaign is API-driven.

How an agent uses MatterSpace

  1. 1Agent specifies target properties, domain constraints, and campaign mode via API or MCP.
  2. 2MatterSpace auto-selects the domain pack, dynamics parameters, validation tiers, and scoring objectives.
  3. 3Campaign runs autonomously. Agent receives typed artifacts — candidate structures with scores, constraint satisfaction records, and provenance.
  4. 4Agent evaluates Pareto front, selects candidates for synthesis or further analysis, and can launch follow-up campaigns referencing prior results.

MatterSpace Lattice

Materials discovery. End to end.

MatterSpace Lattice is the first deployment of the universal engine. 9 domain packs covering the most important classes of functional materials. Ready.

Battery Cathodes

Ionic conductivity, voltage stability, and thermodynamic ground states for advanced energy storage.

Catalysis

Surface geometries and compositions optimized for target binding energies and reaction pathways.

Superconductors

Crystal structures with target critical temperatures and electronic properties under extreme conditions.

Magnets

Permanent magnet compositions with optimized magnetocrystalline anisotropy and Curie temperatures.

Photovoltaics

Band gap engineering for solar cell absorbers. Direct-gap semiconductors with optimal carrier properties.

Thermoelectrics

Materials with high Seebeck coefficients and low thermal conductivity for waste heat recovery.

High-Entropy Alloys

Multi-principal-element alloys with target mechanical, thermal, and corrosion-resistance properties.

Electrolytes

Solid-state and liquid electrolyte compositions with optimized ionic transport and electrochemical stability.

Coatings

Protective and functional surface coatings with target hardness, adhesion, and environmental resistance.

What makes Lattice different

Symmetry by Architecture

The engine respects rotational, translational, and permutational symmetries by design — not by data augmentation. Fewer training samples, no spurious symmetry-breaking artifacts.

Valid by Construction

Crystal symmetry groups, bond-length bounds, coordination numbers, and charge neutrality are enforced during generation. Every output is physically valid. No post-hoc filtering required.

Diversity, Not Just Quality

The evolutionary outer loop maintains a structured archive of diverse, high-quality candidates. You get a Pareto front of alternatives — ionic conductivity vs. stability, hardness vs. ductility — not a single answer.

Reproducible by Default

Every campaign produces deterministic replay recipes. Configuration snapshots, dynamics trajectories, random seeds, and constraint satisfaction records. Re-run any campaign and get the same candidates.

How We Differ

Three paradigms. Only one generates valid science.

MatterSpace is an engine, not a wrapper. Built from first principles to enforce constraints during generation. Chemistry AI labs, traditional computational methods, and MatterSpace take fundamentally different approaches to discovery.

Chemistry AI Labs

  • Post-hoc filtering of invalid outputs
  • No physics constraint enforcement
  • Screening, not discovery
  • Single-domain tools
  • No provenance or replay

Traditional Computational Labs

  • Full physics grounding
  • Hours to days per candidate
  • No generative capability
  • DFT-only, exhaustive enumeration
  • Manual provenance tracking

MatterSpace

  • Constraints enforced during generation
  • Physics-grounded energy landscapes
  • Fast generative discovery
  • Universal engine, domain packs per field
  • Deterministic replay and full provenance
RL / Autoregressive
DFT / Brute Force
MatterSpace
Physics grounding
None
Full
Learned + enforced
Constraint enforcement
Post-hoc filter
Built-in
During generation
Speed
Fast
Hours–days / candidate
Fast
Diversity
Mode collapse
Exhaustive but slow
Pareto front by design
Provenance
None
Manual
Deterministic replay
Agent-native
No
No
AI-native

Engine, not model

Diffusion models generate. Engines generate valid.

Diffusion-based generators, crystal VAEs, and RL molecular optimizers produce candidates — then filter out the invalid ones. They are single-domain, single-objective, and non-reproducible. MatterSpace is a complete generation engine: it enforces constraints during generation, optimizes across competing objectives simultaneously, and produces deterministic, provenanced artifacts. One engine. Every scientific domain.

Diffusion & RL GeneratorsMatterSpace
Generation approachDiffusion denoising or RL reward maximizationAdaptive dynamics across learned energy landscapes
Constraint handlingPost-hoc filtering — discard invalid outputsEnforced during generation (valid by construction)
OptimizationSingle-objective (stability or one property)Multi-objective Pareto frontier across competing properties
Domain scopeSingle domain per model (materials OR drugs OR proteins)Universal engine — domain packs per field
DiversityMode collapse toward reward maximumStructured archive of Pareto-optimal candidates
ReproducibilityStochastic, seed-sensitiveDeterministic replay with full provenance
Model flexibilityFixed pre-trained modelBring your own, use ours, or build from scratch inside the engine
ValidationExternal DFT verification requiredMulti-tier validation built into the pipeline

Why MatterSpace

What open-source cannot do.

Four Campaign Modes

Open Discovery, Prototype Optimization, Guided Rediscovery, and Blind Rediscovery. Each serves a different design intent. Open-source models have generate-and-filter.

Valid by Construction

Constraints are enforced during generation, not applied as post-hoc filters. Every candidate that exits the engine satisfies your specification.

Multi-Objective Pareto Optimization

Competing objectives handled natively. The engine navigates trade-off landscapes and returns the Pareto frontier — not a single best guess.

Adaptive Dynamics Controller

Four dynamics modes that switch in real time based on landscape conditions. The controller selects the right strategy automatically.

Domain Packs

Pre-built constraint sets, force fields, scoring objectives, and samplers for each domain. Lattice (9 packs), Pharma, Algo, Tessera, Longevity.

Bring Your Own Model

Use MatterSpace models or plug in your own. The engine trains your model to bias toward your objectives and goals. The strength is the pipeline, not any single model.

Validation

Blind rediscovery of known materials

The ultimate test: can the engine rediscover materials that humans already know exist \u2014 without being told what to look for?

In blind rediscovery benchmark mode, target structures are completely hidden from the generation pipeline. Zero information leakage. The engine explores from physics alone. Post-hoc comparison reveals whether generated candidates match known stable structures.

MatterSpace has passed this test. It has blindly generated candidates that match known materials at the structural level \u2014 confirming that the physics-first approach discovers real science, not statistical artifacts.

Read the full story

3-Level Rediscovery Protocol

Level A — Performance

Generated candidates match or exceed target property thresholds (ionic conductivity, band gap, magnetization).

Level B — Fingerprint

Structural fingerprints of generated candidates match known materials at configurable similarity thresholds.

Level C — Structure

Atomic-level structural comparison. Root-mean-square displacement below threshold against known crystal structures.

Platform

Your agents. Your models. Your candidates.

Define objectives, not datasets

MatterSpace doesn’t need your raw data. Define target properties, constraints, and objectives. Domain packs supply the physics. The engine handles the rest.

Your model, your choice

Use MatterSpace’s built-in models. Plug in your own. Or build a new model from scratch inside the engine. The engine trains your model to bias toward your objectives. The pipeline is the product, not any single model.

Deploy on your terms

Cloud-hosted, self-hosted, or air-gapped. Models you build inside MatterSpace are yours.

Your agents. Our engine.
Universal generation.

One generation engine for every scientific and engineering domain. Agent-first. Domain packs per field. Built from first principles.

LatticeReady
PharmaEarly Testing
AlgoEarly Testing
TesseraEarly Testing
LongevityEarly Testing

MatterSpace is patent pending in the United States and other countries. Vareon, Inc.