> For the complete documentation index, see [llms.txt](https://metafishtank.gitbook.io/metafishtank-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://metafishtank.gitbook.io/metafishtank-docs/12-roadmap.md).

# 12. Roadmap

The roadmap is designed around proof of persistent Agent utility rather than the number of games launched.

## Phase A — BNB Foundation

* deploy and test EVM-native MAP contracts;
* BSC wallet integration;
* minting flow;
* indexer and state services;
* Solidity unit / invariant / fuzz testing;
* storage and gas profiling;
* contract verification;
* eligible legacy provenance snapshot-and-claim flow where required.

## Phase B — Test Seasons T1–T3 (Public Beta Season 2)

* launch BNB edition of Drawafish;
* three test seasons, each with 42 days of play plus 7 days of review;
* FP-only participation, with no token rewards during testing;
* test creation and Agent persistence;
* measure retention, uniqueness and social interaction;
* game-airdrop eligibility (10 million $MFT budget) with independent identity review;
* anti-bot / anti-Sybil calibration;
* indexer stress testing, gameplay and SDK feedback;
* re-run and calibrate the economic model with real test-season data, and publish that data.

## Phase C — TGE and Official Season S1

* $MFT launch and official liquidity pool;
* third-party audit of core contracts completed and report published;
* production MAP deployment and finalized creation / minting flow;
* official fish raising (game mining) and staking;
* public on-chain dashboard;
* contract and security documentation;
* marketplace features only when security and product readiness justify them.

## Phase D — Reference Game Expansion

* Aqua Arena;
* Predator Protocol prototype;
* deeper Agent progression;
* ECS developer attribution testing;
* cross-game achievement write-back;
* richer Agent memory.

## Phase E — Open Ocean SDK

* TypeScript SDK;
* Unity toolkit;
* Unreal toolkit;
* public adapter documentation;
* developer sandbox;
* game namespace tools;
* attribution dashboard.

## Phase F — Agent Economy Compatibility

* ERC-8004 adapters where useful;
* evaluate emerging BAP-578 compatibility;
* BNB Agent SDK integration where useful;
* Agent commerce and payment experiments;
* portable reputation and validation modules.

## Phase G — Scale

* larger third-party game network;
* Open Ocean discovery and distribution;
* optional opBNB execution modules where justified;
* expanded state indexers and data services;
* advanced Anima Developer Runtime;
* high-fidelity Agent representation research, including the long-term Abyss Horizon vision.

The roadmap is directional. Specific dates and launch conditions should be published separately as engineering, security and ecosystem dependencies become measurable.


---

# 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://metafishtank.gitbook.io/metafishtank-docs/12-roadmap.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.