THE ENGINE LIBRARY

Real tools.
Inspectable results.

22 scientific tools and 6 Discovery study tools, one MCP connection. Six optional composition tools add typed capability discovery, dependency planning, checked execution and robust scheduling. Three separate network tools support the fixed-workload contributor network. Understand the method, reproduce a calculation and keep its limitations in view.

Discovery: choose observations, challenge results and improve a schedule →

Build a Rust engine for ScoreCompute →

Method guides: GUM vs Monte Carlo uncertainty propagation · GRIM and GRIMMER arithmetic screening · What a signed receipt proves

shape_the_sound

Inverse acoustic design ↗

Ask Rust to find an ideal fixed-edge membrane matching requested frequency ratios, then inspect its computed shape, vibrations and numerical limits.

check_arithmetic

Arithmetic verification ↗

Check bounded scalar expressions with exact rational arithmetic where supported, declared tolerances and conservative inconclusive results for floating estimates.

kepler_stability

Kepler sensitivity ↗

Survey a bounded grid of initial orbits in a planar Sun–Jupiter model, with finite-window sensitivity, integrated durations and numerical diagnostics.

hear_the_shape

Shape and sound ↗

Compute vibration modes of a supplied polygon, inspect its nodal patterns and compare the spectra of two shapes under an ideal membrane model.

propagate_uncertainty

Uncertainty propagation ↗

Compare first-order uncertainty propagation with seeded Monte Carlo for an explicit measurement model, checking physical units before calculating a result.

plan_golden_hour

Golden hour ↗

Compute golden and blue light windows for one UTC day from explicit geometric solar elevation bands, with separate conventional sunrise and sunset crossings.

triangulate_tracks

Multi-observer triangulation ↗

Estimate a moving object’s position and velocity from timed azimuth/elevation measurements at different locations, with model-based uncertainties and explicit geometry limits.

route_optimizer

Route optimization ↗

Order supplied points into a complete geometric tour with bounded Rust CPU computation, exact small-instance search and explicit heuristic limits.

simulate_pi

Monte Carlo ↗

Estimate π with seeded Monte Carlo sampling on CPU or NVIDIA CUDA, with a Wilson confidence interval and reproducible results.

optimize_tasks

Optimization ↗

Select the highest-value combination of independent tasks under an integer time budget using an exact Rust knapsack solver.

simulate_plan

Schedule simulation ↗

Estimate how often a selected task schedule stays within budget by simulating independent duration uncertainty.

compute_orbit

Orbital mechanics ↗

Compute an ideal two-body elliptical orbit with a Rust solver for Kepler’s equation, including trajectory and orbital period.

verify_shadows

Sun and shadows ↗

Compare measured shadow geometry with a calculated solar position using control points, a homography and Monte Carlo uncertainty.

check_ephemeris

Ephemeris ↗

Compare a claimed Sun or Moon position with an approximate ephemeris for a UTC timestamp and geographic location.

audit_statistics

Statistical audit ↗

Screen reported means and standard deviations for arithmetic inconsistency under an integer-valued data model.

analyze_kinematics

Kinematics ↗

Translate an observed angular speed into transverse speed under explicit distance assumptions.

check_shadow_track

Shadow tracks ↗

Compare measured shadow directions over time against expected solar motion at a specified place and date.

solve_equilibrium

Game theory ↗

Explore a small imperfect-information game with a Rust self-play solver and compare its result with a known equilibrium value.

analyze_chess_game

Chess analysis ↗

Compare supplied chess moves with Stockfish recommendations and inspect an aggregate move-quality profile.

screen_wash_trading

Market patterns ↗

Inspect supplied trade records for dense round-trip patterns and repeated volume within a price band.

tour_profile

Instance profile ↗

Inspect distances, isolation and shape in a planar point cloud (3–256 points), with explicit handling of coincident points and undetermined principal axes.

scan_counterexample

Counterexample scan ↗

Bounded deterministic search for a counterexample to a declared arithmetic claim over a discrete parameter box.

First published 30 September 2026 · Last updated 2 November 2026