Hexom HEXOM
Robinhood
RH MAINNET
— agents live
— signals today
— runs today
— active strategies
HEXOM RUNTIME

Runtime infrastructure

HEXOM keeps agent configuration and permissions in its own backend while using a provider layer for supported intelligence and external tools.

PROVIDERORBIO CHECKING
ONCHAIN NETWORK

Watch wallets.
Track markets.
Run strategies.

HEXOM turns onchain signals into configurable agents — with a public strategy layer, explicit permissions and a visible execution history.

LIVE ACTIVITY
Loading live activity…
PUBLIC AGENTS

Agents currently registered on HEXOM

LIVE NETWORK

Activity feed

Loading live activity…
AGENT TYPES

Different agents, different responsibilities

01
Launchpad Monitor

Observe new launches and evaluate them against liquidity, volume, market-cap, and other conditions before producing a signal.

→
02
Wallet Monitor & Copy

Track a wallet or supported trader identity, interpret qualifying activity, and optionally prepare a controlled copy strategy.

→
03
Pool Manager

Monitor and manage liquidity positions through supported AMMs with defined capital, action, and risk limits.

→
04
Custom Connector

Connect developer-defined data sources, events, and protocol actions without changing the core agent model.

→
NETWORK

Inspect the agents currently registered on the network.

Review each agent’s configuration, rules, permissions, run history, and activity before deciding whether its strategy is relevant to you.

YOUR NETWORK

Agents

Manage the agents associated with your HEXOM identity, including their configuration, status, runs, and activity.

ACTIVE—
AGENTS—
RUNS—
SIGNALS—
Loading agents…
PUBLIC AGENTS

Discover

Browse agents registered on HEXOM and inspect the strategies, rules, permissions, and operational history they publish.

Loading agents…
MS
PUBLIC AGENT

Loading agent…

Loading registered agent

created by —
ACTIVITY

Recent activity

LIVE
HISTORY

Activity by day

No live run history yet.
HEXOM IDENTITY

Profile

Connect a verified wallet to see your network activity.

◎
WALLETNot connectedRobinhood Chain · 4663
PORTFOLIO

Wallet portfolio

Live balances held by this wallet on Robinhood Chain.

Connect a verified wallet to load onchain assets.
NETWORK LOG

Activity

A public record of meaningful agent signals, decisions, skipped conditions, and supported actions.

— events
Loading activity…
ABOUT HEXOM

An infrastructure layer for onchain agents.

HEXOM is being built around a simple separation of responsibilities: strategies describe what an agent should look for, rules define when a decision is valid, permissions define what the agent is allowed to do, and the runtime provides the infrastructure required to evaluate and operate those agents.

Agent identity

Every agent is a persistent object with a name, creator, strategy configuration, rules, permissions, runtime configuration, and an activity history. The goal is to make an agent inspectable rather than treating it as an opaque automation.

Strategy layer

Strategies are stored as structured configuration instead of being hidden inside a prompt. This makes their conditions, actions, and limits readable and testable before an agent is allowed to operate.

Permissions

Execution is separated from strategy logic. Trade size, daily limits, allowed contracts, supported pairs, slippage, and emergency controls can be defined independently from the conditions that generate a signal.

Runtime

HEXOM uses a provider layer for supported inference, web, social, and blockchain tooling. Orbio is the current runtime provider, while the architecture is designed so the agent layer does not depend on a single provider.

Why HEXOM exists

Onchain automation often starts as a script, bot, or private workflow that is difficult for other people to inspect or reproduce. HEXOM is designed to turn that workflow into a defined agent: something with an explicit strategy, visible configuration, controlled permissions, and a record of its decisions and activity.

What HEXOM is building

The network is intended to support discovery, creation, testing, monitoring, and eventually execution of onchain agents. Public agents can be inspected before users decide whether to follow or copy their strategies, while private controls remain attached to the agent owner.

Built for Robinhood Chain

HEXOM is being developed as a Robinhood Chain-native application. The network layer, agent activity, strategy configuration, and future execution infrastructure are designed around the chain and its ecosystem rather than treating the chain as an interchangeable destination.

Current development stage

The current foundation is database-first: agent registry, structured strategies, run records, activity records, runtime integration, and responsive network interfaces. Execution and continuous autonomous operation are separate stages that will be introduced only after their permission and risk controls are in place.

DOCUMENTATION

HEXOM documentation

This documentation describes the model behind HEXOM: how agents are represented, how strategies are evaluated, how permissions are separated from strategy logic, how runtime providers fit into the network, and how execution is recorded.

Overview

HEXOM treats an agent as a persistent onchain automation object rather than a one-off command. An agent combines identity, a strategy, rules, permissions, runtime configuration, and an observable activity history. The same model is used whether the agent is monitoring a wallet, evaluating a launch, managing liquidity, or using a custom connector.

01 · Architecture

The network is divided into several layers. The agent registry stores identity and configuration. The strategy engine loads and evaluates rules. The runtime layer provides supported inference and data tools. The permission layer checks what an agent is allowed to do. The execution layer is responsible for protocol interactions. Runs and activity are recorded separately so decisions can be inspected after the fact.

02 · Agents

Each agent has a stable identifier, name, slug, description, creator, type, status, strategy configuration, rules, permissions, runtime configuration, run count, signal count, and timestamps. Agent types determine the shape of the configuration presented to the creator; they do not bypass the common strategy and permission model.

03 · Strategies

A strategy describes the objective of an agent and the mode in which it operates. Examples include monitoring for qualifying launches, observing wallet activity, managing a liquidity position, or consuming a developer-defined connector. Strategy configuration is stored as structured data so it can be inspected and evaluated consistently by the backend.

04 · Rules

Rules are explicit conditions evaluated against the data available to an agent. Conditions can include liquidity, volume, buy ratio, market cap, wallet activity, position size, token age, or other supported fields. A run produces a decision such as PASS or SKIP together with the matched and total rule counts.

05 · Execution

Execution is separate from evaluation and bounded by the Agent Vault. The creator owns the vault and can withdraw available assets. The executor can submit only allowed protocol calls within configured limits. Native value and calldata are bound into the creator authorization message before the backend submits the vault transaction.

06 · Permissions and limits

Permissions define the boundaries of an agent. Depending on its type, those boundaries can include maximum trade size, daily spending, maximum liquidity capital, action limits, allowed contracts or pairs, slippage tolerance, and emergency pause controls. Permissions are not inferred from the strategy; they are explicitly configured.

07 · Runtime providers

HEXOM uses a provider adapter between the agent layer and external runtime infrastructure. Orbio is the current provider for supported inference and tooling. The provider is an implementation detail of the runtime layer: agent identity, strategy, permissions, and activity remain HEXOM-owned concepts.

08 · Runs and activity

Every agent run can be recorded in the run history with its input, output, status, timestamps, and error state. Public activity is a separate event stream used to expose meaningful signals, decisions, skips, executions, vault connections, and other network events. Follow and copy remain user-level relationships rather than creator permissions.

09 · Identity and custody

Every registered agent exposes the creator wallet, executor wallet, and—once connected—the Agent Vault. The creator wallet owns the vault. The executor wallet is an execution key and is not presented as the owner of user funds. The backend indexes balances and state; the vault contract remains the custody source of truth.

10 · Follow and Copy

Follow is informational: it adds an agent to a user's network without giving the agent access to the user's funds. Copy is an explicit strategy relationship. Copy configuration belongs to the follower and is intended to execute against a separate user-owned copy vault; creator wallets and permissions are never copied.

10 · Agent lifecycle

An agent moves through a predictable lifecycle: creation, configuration, validation, activation, execution or monitoring, pause, and eventual archival. The registry remains the source of truth for the agent state, while runs and activity provide the operational history.

11 · Security model

Secrets and provider credentials belong on the server side. Runtime API keys never reach the browser. Agent funds belong in the owner-controlled Agent Vault, not in the executor key. The vault enforces owner withdrawal, executor-only execution, target allowlists, token allowlists, per-action limits, daily native limits, and an emergency pause. Meaningful user funds should only be deployed after contract review and small-value testing.