Skip to main content

FrootAI — AmpliFAI your AI Ecosystem Get Started

⚡ Lean Mode · measured savings

Same fruit, none of the sugar.

Every FrootAI primitive ships in two flavors — 📖 Full (the verbatim source) and ⚡ Lean (compressed, fewer tokens). Every Lean variant clears the fidelity gate: guardrails, parameters, and code blocks are preserved exactly. The numbers below are the exact o200k_base token counts across the whole catalog — measured, not estimated.

FrootAI · Lean Mode receipt
1,518,3201,510,081tok
Full catalogue1,518,320 tok
Lean catalogue1,510,081 tok
You save8,239 tok
Saved−0.54%
Fidelity10 / 10
Primitives1,063 · 964 ⚡
Measured · o200k_base · lossless floor
every Lean variant cleared the fidelity gate
Primitives
1,063
964 with a Lean variant
Full tokens
1,518,320
exact o200k_base
Lean tokens
1,510,081
−8,239 saved
Mean fidelity
10/10
gate-verified

Savings rate by type

Relative scale — bars are sized against the best-performing type; the figure on each row is the exact measured saving (the lossless floor).

Skills0.61% · −5,382 tok
Agents0.3% · −857 tok
Instructions0.54% · −1,827 tok
Hooks1.15% · −173 tok

Fidelity distribution

Every shipped Lean variant must clear the fidelity gate — guardrails, parameters, and code blocks preserved exactly. The bar at 10/10 is full because nothing ships below it.

100%of 964 shipped Lean variants verified at a perfect 10/10
10/10964
9/100
8/100
7/100
6/100

Savings by primitive type

TypeLean / totalFull tokLean tokSavedSaved %Fidelity
Skills638 / 638882,159876,7775,3820.61%10/10
Agents139 / 238284,436283,5798570.3%10/10
Instructions176 / 176336,672334,8451,8270.54%10/10
Hooks11 / 1115,05314,8801731.15%10/10
Ecosystem964 / 1,0631,518,3201,510,0818,2390.54%10/10

How we measure

Exact tokenizer, not chars ÷ 4

Every count is the exact o200k_base token count (the GPT-4o / GPT-4.1 vocabulary) — the same tokenizer the model sees. We never estimate from characters or bytes, which over- or under-counts depending on content.

Gate-consistent Full basis

A primitive's Full count is tokensLean + savedTokens — the exact pair the fidelity gate compared. We deliberately avoid mixing measurement bases, so a saving can never be inflated by a field measured a different way.

Lossless compiler only

Today's Lean compiler is deterministic and byte-faithful: it reclaims whitespace, verbosity, and duplication — nothing semantic. That is why the savings here are a modest, honest floor rather than a headline.

Fidelity gate, every variant

A Lean variant only ships if it preserves guardrails, parameters, and code blocks exactly — scored 10/10. Anything that loses meaning is served Full and counts as zero saving here, never a hidden win.

The numbers above are computed at build time from the published catalog by the same tested aggregator our CI pins — so this page can never disagree with the gate.

What it costs you

Plug in your model's input price to see the catalog's token cost — and what Lean trims off each full load. The numbers come straight from the measured token counts above.

Full / load
$15.18
Lean / load
$15.10
Saved / load
$0.082
Saved across 1 full-catalog load$0.082

Honest math: the saving is savedTokens ÷ 1,000,000 × price × loads. It is small because today's Lean compiler is lossless — the dollars scale only with how often you load the full catalog. Presets are examples; enter your model's real input price.

This is the lossless floor. Today's Lean compiler is deterministic and byte-faithful — it reclaims whitespace, verbosity, and duplication only, so savings are modest but every token is provably safe. Semantic Lean+(a later phase) targets larger reductions; we will only publish a number once it's measured here, against the same fidelity gate. Browse the catalog →