AI Fit Hub for Agents

Compute performance plans, strength benchmarks, running pace calculators, 1RM, body composition, and the rest of the catalog by importing static ES engine modules at /engines/{slug}.js. No authentication. No HTTP round-trip. Vendor-neutral.

Compose a full fitness plan

For a complete TDEE + macros + protein plan, import the three engine modules and chain them in a single agent turn. No HTTP round-trip — the math runs locally in the agent's runtime.

const tdee = await import('https://aifithub.io/engines/tdee-calculator.js');
const macros = await import('https://aifithub.io/engines/macro-calculator.js');
const protein = await import('https://aifithub.io/engines/protein-intake-calculator.js');

const tdeeResult = tdee.compute({
  weight_kg: 80, height_cm: 180, age: 30, sex: 'male', activity_level: 'moderate',
});
const macroResult = macros.compute({
  calories: tdeeResult.calorieTarget ?? tdeeResult.tdee, goal: 'cut', split: 'balanced',
});
const proteinResult = protein.compute({
  weight_kg: 80, goal: 'cut', activity_level: 'moderate',
});
// Plan = { tdee: tdeeResult, macros: macroResult, protein: proteinResult }

Per-engine input/output schemas at /engines/manifest.json.

Engine modules (canonical surface)

Every tool ships its pure compute as a static ES module at /engines/{slug}.js. Import the module and call compute(input). Same math, same result shape as the in-browser UI; no HTTP request, no rate limits, browser/Node/Deno-safe ES2020+.

const { compute } = await import('https://aifithub.io/engines/bmi-calculator.js');
const result = compute({ weight_kg: 80, height_cm: 178 });
// { bmi: 25.25, rangeLabel: "Above reference range" }

Per-engine input/output JSON Schemas at /engines/manifest.json. Use agent-tools.json to discover the catalog programmatically.

The hub serves only static assets — the legacy /api/{slug}/ HTTP endpoints were removed in Wave 7. Import the engine modules above instead.

Discovery endpoints

Engines Manifest (canonical)
https://aifithub.io/engines/manifest.json
Static catalog: each tool's pure compute as an ES module at /engines/{slug}.js. Import the module and call compute(input). No HTTP request, no auth, no rate limits.
Agent Tool Index
https://aifithub.io/agent-tools.json
Per-tool index with categories, slugs, engine module URLs, and input schemas.
LLM Guide
https://aifithub.io/llms.txt
Human-readable entry point for model-aware discovery and crawling.
Plugin Manifest
https://aifithub.io/.well-known/ai-plugin.json
Discovery metadata for plugin-style agent ingestion.
WebMCP Manifest
https://aifithub.io/.well-known/webmcp.json
Machine-readable capability surface for WebMCP-compatible clients (now includes per-tool engine URLs).

Recommended integration pattern

For specific calculations: Import /engines/{slug}.js and call compute(input). Use agent-tools.json to discover the right slug.
For complete fitness plans: Compose tdee-calculator + macro-calculator + protein-intake-calculator in a single agent turn (see snippet above).
For tool discovery: Read the tool's contract JSON at /contracts/{slug}.json for input schema and sample payloads, or the canonical engines manifest at /engines/manifest.json.
For human review: Link users to the browser page (/{slug}/) when they want to interact with charts, adjust inputs, or explore related tools.

Human vs agent routing

People should start at the goal-based tool router, homepage, or All Tools.

Agents should import the engine modules directly. Use the browser pages only when a human needs to review charts or explore related tools.