STEM
MentalForge
Mental-calculation flagship for ages 9–14: sprint drills + a trick lab (left-to-right, make-a-ten, doubling, soroban, ×11, squaring) on a deterministic engine that grades every answer. A small cast each embody one calculation strategy you say out loud.
#2E7D6B MentalForge is a mental-calculation gym: fast sprints and a trick lab where every strategy — left-to-right, make-a-ten, doubling, the ×11 trick, squaring near a base — is a character whose defining act IS the method. A deterministic engine grades every answer (an LLM never goes near the arithmetic), so the maths is always right. Ages 9–14, usable to 18.
Distributed-narrative cast
Meet the cast
MentalForge's mental-math cast each embody ONE calculation strategy you say out loud (R-DN-PARITY); mentor Abaca sets the sprint and coaches the trick.
Lefty
Left-to-right — add the biggest places first, not last
Read chapter →
Tenna
Make-a-ten — round up to a friendly ten, then adjust back
Read chapter →
Halvor
Double & halve — double one factor and halve the other
Read chapter →
Soro
Soroban beads — picture the beads to add and subtract fast
Read chapter →
Squill
Square near a base — square numbers close to 10, 50, or 100
Read chapter →
Elva
The ×11 trick — add each pair of neighbouring digits
Read chapter →
Grandel
Subtract from a round number — take from 100 or 1000 by complements
Read chapter →
Crisca
Cross-multiply — two 2-digit numbers in one criss-cross
Read chapter →
Nina
Cast out nines — a quick check that catches most slips
Read chapter →
Rounda
Estimate first — get close, then check the exact answer looks right
Read chapter →
Splitt
Break apart — split a hard product into easy distributive pieces
Read chapter →
Abaca
(Mentor) — the mental-math coach who sets the sprint and reflection
Read chapter →
Browse all chapters → · What's distributed-narrative methodology? →
What's inside
Learning goal
Mental-calculation flagship for ages 9–14: sprint drills + a trick lab (left-to-right, make-a-ten, doubling, soroban, ×11, squaring) on a deterministic engine that grades every answer. A small cast each embody one calculation strategy you say out loud.
Question kits
16 curriculum-aligned kits × 25 questions = 400 questions per app, mapped to recognized standards.
On-device AI mentor
FoundationModels-powered hints, feedback, and adaptive difficulty — all running locally.
Mentored by Abaca — on-device AI, no data leaves the device.
How MentalForge handles your kid's data
- ✅ All progress, settings, and AI-generated content stays on the device
- ✅ No analytics, no tracking, no third-party SDKs
- ✅ No ads, no in-app purchases — you pay once
- ✅ COPPA compliant under the 2026 FTC amendments
- ✅ Parental controls + session limits + content filters built in
MentalForge runs on ForgeKit — the open-source Swift Package Manager framework that powers every Spark & Anvil app. ForgeKit ensures consistent accessibility, COPPA compliance, and design language across the portfolio, so your kid's progress and preferences feel coherent across every app they touch.
Coming to the App Store
MentalForge is in active development. Email us to hear when it ships — no marketing, no spam, just a one-shot launch announcement.
Email me at launch