Pixel art compiler for indie developers that keeps game art consistent
GPU-accelerated rigid-body dynamics solver for robot learning
Stage
Not given
Not given
Founded
Not given
Not given
Based in
US
Not given
Pricing model
Freemium
Open source
Pricing
Free plan with 3 saves and 100 agent credits. Full access for $15 one-time during early access (regular price $20), includes unlimited saves and all features with 14-day refund. Agent plan subscription at $8/month or $80/year includes everything plus 2,000 monthly agent credits.
Not given
Key features
Build sprites from simple shapes like blobs, capsules, boxes, triangles, and rings
Define style profiles with light direction, color ramps, outlines, dithering and textures
Deterministic rendering - same asset always compiles to identical pixels
Extract style from reference images and import Lospec palettes
Create asset variations with rerolled seeds sharing silhouette and palette
VFX Forge with layered particle emitters and curves over particle age
Export to multiple formats: PNG, sprite sheets with JSON atlas, GIF, APNG, Godot, and Unity
AI agent integration through MCP for asset and palette creation
Cloud save for documents across devices
Royalty-free commercial license bundled with exports
3.8× PhysX throughput on 20 benchmarks geometric mean
13.0× performance on heterogeneous task mixtures
Per-environment work scheduling for efficiency
Reduced-coordinate articulation dynamics
Differentiable simulation
Rigid-deformable coupling support
Compliant and hydroelastic contact
62% less GPU memory than PhysX at matched batch size
3.90 million environment steps per second peak throughput
What makes it different
Keeps all assets automatically consistent through unified style profiles and palettes
Deterministic composition ensures no drift between assets or versions
Works in browser with no AI - full artist control through deterministic rules
Connect AI agents to build assets in your style without drift or variation
Ready exports for major engines with standard file formats
Designed for heterogeneous workloads with different robots and tasks simulated together efficiently
Integrated into open-source Newton for seamless adoption without separate physics stack
Supports diverse physical interactions beyond rigid bodies
Enables scaling of diverse robot experience for general-purpose learning
Spritory
Steel