Safety & Disclaimer

No performance claims

Every number, snapshot, example log, and backtest in this project is illustrative/demo unless you feed it real data. Nothing here represents historical performance. The backtester checks whether rule logic is internally consistent, not whether a strategy is profitable, and feeding it real bars does not create a track record. On-chain figures are either a real read or honestly empty, and today they read zero: no TVL, no depositors, no trades.

Scope

Aelix is deliberately narrow: equities-only, long-only, USD, human-in-the-loop, Claude-Code-native. Options, futures, and crypto are not supported by the underlying beta, and the desk is configured to refuse them (option order tools are deny-ed).

Your responsibilities

• Fund the Agentic account with a small budget you can afford to lose, that is your maximum downside.
• Define your risk caps in `strategies/` before trading; the Risk Manager VETOes if they are unset.
• Monitor it yourself. You own the guardrails and the limits; the agent will not change them.
• Keep the repo private, and never commit secrets or the OAuth token. See Configuration.
• Verify anything the desk surfaces before acting on it. It is a second opinion, not a decision-maker.

Open verification items

Some assumptions still need confirmation against official sources before you rely on them:

Instrument scope

Robinhood Agentic Trading is currently beta and equities-only, crypto/options/futures support is not available. The desk is intentionally limited to equities long-only; confirm current scope with Robinhood.

MCP tool names & behavior

Verify the real tool names via /mcp or claude mcp get robinhood-trading, then tighten `.claude/settings.json` to match. Names can change during beta.

Legal

Any feature beyond equities could fall under securities regulation and must pass legal review before it is even considered. No legal review has been completed, and deploying a contract does not resolve regulatory exposure, including the US-person question.

Third-party audit (on-chain module)

Not done. Two internal audit passes and a 42-agent preflight review are not an audit. Nothing on chain should be relied on until an independent audit exists.

Explorer verification

The mainnet contracts are not yet verified on the block explorer, so you cannot yet read the deployed source there. Verify addresses against onchain/deployments/latest.json and by direct call.

One item has left this list: the ownership handover is complete as of 2026-07-26, every owner-controlled contract is owned by the 2-of-3 Safe, read back by direct call. It is a fact now, not a plan, and it changes none of the items above.

Out of scope: crypto / token material

The on-chain module: on mainnet, and unaudited

One correction to what this page used to say. The on-chain vault + guardrails-as-code module in onchain/ is no longer testnet-only: as of 2026-07-26 it is deployed to Robinhood Chain mainnet, chainId 4663, against real periphery. This page previously claimed the opposite, that claim was out of date and has been corrected rather than quietly softened, and every caveat around it stands.

A second correction, this one in the other direction: the ownership handover that this page listed as incomplete is complete. On 2026-07-26 the 2-of-3 Safe called acceptOwnership() on RWAVault, ChainlinkOracleAdapter and SessionKeyExecutor in one batch, pendingOwner() now reads zero on all three, and GuardrailConfig and UniswapSwapAdapter were Safe-owned from construction. So every owner-controlled contract in the stack is owned by the 2-of-3 Safe: changing a risk cap, a price feed, the deposit cap or a session grant takes two of three signatures, and the deploy key reverts with OwnableUnauthorizedAccount on all of them. There is no timelock yet: a change the Safe signs takes effect in one transaction. And multisig custody is a statement about custody, not about code, it does not make the contracts audited.

What the deploy and the handover do not change is more important than what they do. Every item below is current:

• No third-party audit. Two internal audit passes and a 42-agent preflight review are not an audit. This is the single largest caveat on the module.
• Multisig ownership is not a safety property of the code. Two of three signatures are now required to touch any owner-controlled setting, which removes the single-hot-key risk, and removes nothing else on this list. There is no timelock yet — an owner change takes effect in one transaction, with no delay for anyone to react.
• No track record, no returns, no performance. TVL is 0, there are no depositors, and no trade has been made. Any figure shown anywhere is a real on-chain read, honestly empty, or explicitly labelled sample.
• Deposits are capped at 10,000 USDG — an owner-changeable setting, not structural — and the contracts are not yet verified on the block explorer.
• The stop-depth cap is not live yet. The live vault requires a stop below entry on every buy; the cap on how deep that stop may sit (stopLossBps) is enforced in the current repo code, regression-tested, and ships with the next deploy. It is not a property of the live vault today.
• There is no Chainlink sequencer uptime feed on Robinhood Chain. Aelix substitutes a chain-liveness quorum built from 24/7 crypto feeds. It is coarse by design, it catches multi-hour outages, not minute-scale ones, and it is not equivalent to a real uptime feed. See Architecture.
• Legal and securities review is still pending, including the US-person question. The Robinhood Stock Tokens the vault trades are price-tracking instruments, not shares, and are not for US persons. Deploying a contract does not resolve regulatory exposure.
• It is not a live product feature for customer money. The vault holds none, it is not connected to your Robinhood account, and it is not part of the desk's trading path.
• The equities desk is unchanged. It still requires your explicit in-session approval for every order. Neither the mainnet deploy nor the handover makes the desk autonomous.

So the desk's scope stays exactly what it is today: equities-only, long-only, human-in-the-loop, Claude-Code-native. Until legal review, a third-party audit, a technical verification of any third-party network, and official confirmation of non-equities availability are all complete, the on-chain module stays a direction, deployed but unaudited code, not a product you can rely on.

Not affiliated

Aelix is an independent, educational reference architecture built on Claude Code and the Robinhood Agentic beta. It is not endorsed by or affiliated with Robinhood or Anthropic. Licensed under MIT, see the LICENSE file.

Related reading: Guardrails, Strategies & Risk, and the FAQ.