Melaya · Build high-trust AI agents for any workflow, and put them on your phone. The visual agent builder, with Device Control as its flagship: Claude Code, GPT, or Gemini operating your real phone apps, one verified action at a time, with your approval on every action.

Melaya Mobile · Web3 & Crypto

Wallet routines, run for you.Nothing moves without you.

Agents run your on-device wallet and exchange app routines: open the dApp, complete the interaction, log the result, move to the next account. Every transaction and signature pauses for your explicit approval, so nothing moves without you. dApp teams use the same agents to simulate real multi-device usage before mainnet. Full run history for every wallet, every session.

See the pipelines ↓
01
// What breaks today

The status quo costs more than the agent does.

Three pains every sales and BD team hits weekly. Each one is what your reps actually complain about, not what a feature page would call them.

  1. 01

    Airdrop eligibility, exchange actions, and pre-mainnet testing all demand repeated, hands-on activity across wallets and devices.

  2. 02

    Doing it manually eats the ROI.

02
// Pipelines you can build

Compose. Approve. Replay.

Every pipeline below is a shape you wire on the canvas using the crew and tools further down. Not a feature we ship for you, a pattern you configure.

P01

Airdrop eligibility routines

Open the dApp, complete the interaction, log the result, move to the next account. Every transaction pauses for your explicit approval.

P02

Exchange app actions

Run your exchange app routines on your real device. Signatures and transfers wait for your one-tap approval, so nothing moves without you.

P03

Pre-mainnet dApp testing

Simulate real multi-device usage before mainnet, on physical phones. Full run history for every wallet, every session.

03
// The crew

Wallet operations crew

Real personas from the quant_firm crew. Each ships with a tuned system prompt and a default tool allowlist. Swap models per persona on the canvas.

Execution Specialist

ExecutionSpecialist

Runs the on-device wallet and exchange routines, one verified action at a time.

Portfolio Manager

PortfolioManager

Tracks balances and results across every wallet and account you manage.

Chief Risk Officer

ChiefRiskOfficer

Holds every transaction and signature at the approval gate until you sign off.

Report Writer

ReportWriter

Writes the run history: every wallet, every session, every action logged.

04
// Scoped tools

Only the actions you grant.

Every tool below is a real shared tool from the Melaya bundle. Allowlist per agent; HITL-gate the writes; revoke any of them in one click.

shared/tools/phone/

Operates the wallet and exchange apps on your real device, one verified action at a time.

phone_open_appphone_get_screen_treephone_tapphone_input_textphone_screenshotphone_batch
shared/tools/blockchain/

Reads balances, transactions, and ENS names straight from the chain.

eth_get_balanceeth_get_txens_resolve
shared/tools/etherscan_tools/

Verifies on-chain results after every run: balances, transfers, token movements.

eth_balanceeth_txlisteth_token_transfers
shared/tools/solana_tools/

Covers Solana wallets: balances and signature history per address.

sol_balancesol_signatures_for_address
shared/tools/core/

Research, requests, and the human approval gate that holds every sensitive step.

web_searchhttp_requestpause_for_human
05
// Three knowledge layers

The crew reads what you give it.

Every pipeline ships with three layers of knowledge access. Mix and match per agent on the canvas. No shared vector space with another tenant, no surprise reads, no opaque retrieval.

L1

Static context

includeContext

Per-pipeline documents appended to specific agents' input on every run. The ICP brief, playbook, pricing sheet, or won-deal email corpus. Whatever needs to be there before the agent thinks. You pick which personas get which docs.

L2

RAG retrieval tool

rag_retrieve

A scoped tool granted per-agent. When the agent decides it needs more depth, it queries the workflow's vector store on demand. Same knowledge base as Static context, accessed only when the model asks for it.

L3

Cross-run memory

pipeline_memory

Pipeline-level state that carries from one run to the next. Yesterday's research is in scope for today's follow-up. The crew remembers what it already prospected, what got approved, what was sent. The audit log is the second-order knowledge base.

07
// FAQ

Questions we get every week.

Can an agent sign or send funds on its own?

No. Every transaction and signature pauses the run and waits for your explicit approval. The gate is platform policy, not prompt wording.

Does this work across multiple wallets?

Yes. Agents run the same routine account by account, scoped to the apps you allow, with a full run history for every wallet and session.

Build web3 & crypto pipelines on Melaya.

Sandbox tier is free with no card. Join the waitlist and we will email you the moment a slot opens.

← Back to every use case
Join the community