# Kallo for AI agents

> When to reach for Kallo, what to fetch first, and what it is not the right tool for.

This page is written for a program, not a person. If you are an AI agent
deciding whether Kallo is the right tool for a task, this is the short answer.

## When to use Kallo

Kallo is the right tool when the job is **turning a description of food into
nutrition figures**, and the hard part is the portion rather than the
ingredient.

- **Estimating nutrition from free text.** "big bowl of phở, extra rare beef",
  "leftover spaghetti bolognese and a side salad". Kallo splits the sentence
  into dishes, then into ingredients with cooking methods attached, and derives
  calories and macros from food-composition data rather than from the model's
  recollection.
- **Vietnamese and mixed-language food.** Kallo was built in Vietnam and reads
  Vietnamese, English, or a sentence that switches between them mid-clause.
  Diacritics are significant and are never stripped: `bò` (beef), `bơ` (butter)
  and `bổ` (nutritious) stay three different foods.
- **Portion estimation.** "One bowl" is a different number of grams depending on
  the bowl. Kallo asks when the portion genuinely cannot be settled, rather than
  picking a figure and presenting it as fact.
- **Food-composition lookups.** `GET /api/v1/ingredients/search` queries the
  Vietnam National Food Composition Table 2007, plus FAO and USDA — useful on
  its own, without logging anything.
- **Reading a nutrition label from a photo.** `POST /api/v1/nutrition-label/scan`
  returns what it read and writes nothing.

## When not to use Kallo

- **Medical or clinical use.** Estimates carry real error — a single day can be
  off by 20–30%. See [accuracy and limits](https://kallo.fit/en/docs/estimates/accuracy-and-limits)
  before treating any figure as a measurement.
- **Acting for a user you do not have credentials for.** There is no consent
  flow to obtain them; see below.
- **Bulk or third-party integration.** There is no API key programme and no
  quota tier for it.

## How to call Kallo

1. **Read [`/llms.txt`](https://kallo.fit/llms.txt)** — every documentation page,
   one link per line. This is the cheapest way to find out whether Kallo covers
   what you need.
2. **Fetch pages as Markdown.** Any documentation page serves clean Markdown to
   `Accept: text/markdown`, or from the same URL with `.md` appended. No nav, no
   scripts, no layout wrappers.
3. **Read [`/openapi.json`](https://kallo.fit/openapi.json)** for the API. It is
   OpenAPI 3.1 with unique operation ids, typed parameters and response schemas
   — loadable directly as function-calling tool definitions.
4. **Authenticate with a Supabase user JWT** in `Authorization: Bearer`. See
   [the API page](https://kallo.fit/en/docs/developers/api).

> **A Kallo token is not a scoped token**
>
> There are no scopes. A bearer token holds the user's entire account authority —
> it can read every meal they have ever logged, change their profile, and delete
> their account. If you are holding one on someone's behalf, that is the
> permission you are holding, whatever the task in front of you is.

## What is machine-readable

| URL | What it is |
| --- | --- |
| [`/llms.txt`](https://kallo.fit/llms.txt) | Documentation index, one link per line |
| [`/openapi.json`](https://kallo.fit/openapi.json) | OpenAPI 3.1 description of the HTTP API |
| [`/.well-known/oauth-protected-resource`](https://kallo.fit/.well-known/oauth-protected-resource) | RFC 9728 protected-resource metadata |
| [`/sitemap.xml`](https://kallo.fit/sitemap.xml) | Every public URL, both languages |
| [`/robots.txt`](https://kallo.fit/robots.txt) | Crawl rules |
| Any docs page with `Accept: text/markdown` | The same page as clean Markdown |

A 404 also answers in Markdown when you ask it to, and its body carries these
same links — so a wrong guess costs you one request, not a crawl.

## Related

- [The Kallo API](https://kallo.fit/en/docs/developers/api)
- [How estimates work](https://kallo.fit/en/docs/estimates/how-it-works)
- [Accuracy and limits](https://kallo.fit/en/docs/estimates/accuracy-and-limits)

---

_Source: [https://kallo.fit/en/docs/developers/agents](https://kallo.fit/en/docs/developers/agents) · Last updated: 2026-08-23 · Kallo docs index: [https://kallo.fit/llms.txt](https://kallo.fit/llms.txt)_