Game observability and analytics platform for coding agents to monitor real player performance
GPU-accelerated rigid-body dynamics solver for robot learning
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Freemium
Open source
Pricing
Free: 5,000 play sessions/month, 1 game, 14 days data; Indie: $19/month for 25,000 sessions, up to 5 games, 90 days data; Studio: $99/month for 250,000 sessions, up to 25 games, 400 days data. Extra sessions $1 per 1,000. Self-hosted: free, unlimited on own server.
Not given
Key features
Frame time monitoring and hitch detection on player devices
MCP server integration for coding agents (Claude Code, Codex, Cursor)
Crash and error reporting with context
Custom event tracking for game metrics
Automated playtest bots with seed matching
Dashboard with per-game customization
Player retention and churn analysis
Revenue and conversion tracking
Support for 8 game engines
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
Designed specifically for AI coding agents to understand and fix game issues autonomously
Automated verification of fixes using bots that replay with identical seeds
Analyzes real player data, not synthetic testing
Privacy-first by default with no player identification
Open source self-hosted option with unlimited usage
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