> For the complete documentation index, see [llms.txt](https://docs.tryflox.xyz/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.tryflox.xyz/readme.md).

# Introduction

Supply-side intelligence for tokenized assets on Robinhood Chain.

**Flox measures how much new token supply is about to hit the market against how much the market can actually absorb, sizes a position or refuses it, and writes every call — refusals included — to a tamper-evident log anchored on Robinhood Chain.**

The decision is made by a pure function. A language model explains it afterwards and is never allowed to overrule it.

## In one sentence

Flox watches the supply side of tokenized markets — new issuance, redemptions, tokens moving onto exchanges, scheduled unlocks — compares it against live order-book depth, and answers one question: *can this market absorb what's coming?* When the answer is no, it refuses, and the refusal is published where it cannot be edited later.

## What makes it different

Three claims, each verifiable rather than asserted:

**The decision is deterministic.** `src/score.js` is a pure function — no randomness, no clock, no model call in the decision path. The same inputs produce the same verdict forever. You can read the entire policy in about thirty seconds.

**The record includes the refusals.** Most agents publish their wins. Flox writes every assessment to a hash chain and anchors the head on-chain. Edit any past call and the recomputed chain stops matching what's on mainnet.

**The AI explains, it never decides.** Groq writes the narrative and a forward forecast *after* the verdict is fixed. Its predictions are graded against reality, and the grades join the same tamper-evident chain.

## Live on mainnet

|                      |                                              |
| -------------------- | -------------------------------------------- |
| Network              | Robinhood Chain, chain ID 4663               |
| Attestation contract | `0xAA2Ca918502aaF59f1f14C10A6795fef95A0af54` |
| Credits contract     | `0x9595286Dd99C9bc42e5B52D9557770F1147F9b25` |
| Ruleset              | flox-supply-v1.1.0                           |

Start with [Why Flox exists](/concepts/why.md), or jump to [the console](/using-flox/console.md) to use it.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.tryflox.xyz/readme.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.