A Closed-Loop Intelligence Engine

Sauron isn't a signal feed or a bot framework — it's the synthesis of both, plus everything that connects them. 36 evaluators fuse price, news, macro, COT, options flow and 13F filings into composite signals. A multi-dimensional risk gate prevents stacked exposure across asset classes. Six broker adapters route execution. Every trade is graded, every gate decision audited, every dollar tracked. Then the results feed back into how the next decision gets made.

From Tick to Trade to Truth

Every trade flows through five stages. Each stage's output is logged, audited, and fed back to make the next decision smarter. No black box — every step is inspectable from the Eye.

Closed-loop means a rule that wins for 30 days then drifts negative for 7 will fire a notification, get auto-demoted from live-full back to live-small, and surface in the audit log — without anyone watching.

What the Machine Does,
Every Day.

Drawn from the schedule the platform ships with, read when this page was served: 82 scheduled tasks on one beat, plus the price streams where they are enabled. Markets come in on the left, orders and words go out on the right, and the loop turns around one heartbeat. Hover a step, or tap it on a phone, to read what it runs and how often. Times are UTC.

Feel the Orchestrator

Synthetic trades stream in from the left. Each carries a random USD-beta, equity-beta and sector load. Drop the caps and watch which trades the gate refuses in real time. This is the same logic gate_new_entry() runs against your actual bots once you're inside.

One Screen. Everything Moving.

The Operations Center is the home screen: what the system is doing right now. Live signals arrive on a rail that follows you across every page, fills and gate rejections land as banners the moment they happen, and the headband along the bottom keeps portfolio, exposure, bot state and drawdown in view without a click. Everything below is one page.

Nothing Reaches Live
Without Earning It.

One bot per asset class, each with its own entry logic, sizing, cooldowns and skip reasons — all of them starting on the paper venue. A strategy climbs the ladder only on evidence, and falls back down the moment the evidence stops. Nobody has to be watching.

▼ and back down again — a decayed rule is demoted automatically, with 0 strategies currently on the ladder.

Three Ways to Hold a Thesis.

A personality is not a new engine. It is a coherent preset of the knobs that already decide how a bot behaves — the bar it reads, the volatility its stop and target are cut from, how long a thesis may live, how many bets run at once, how much one stop-out costs. Those knobs used to be set one at a time, and nothing in the platform said which combination was a trading style and which was a typo. Three of them are named now: each graded over a window that matches its own holding period, each with its own band in the account allocator.

No personality borrows to fund a position. None of the three sets a leverage or a margin knob — the preset is timeframes, stop and target multiples, a hold ceiling, a concurrency limit and a risk fraction, and that is the whole list. What the short-term one actually gets is how much position one fixed risk budget buys when the stop is tight, plus how many bets may run at once. Both are cash. Where leverage exists at all it is the broker's, on the venues that are built that way, and this platform reports it back to you as a fact at the confirm step instead of offering it as a dial to turn up. And a personality moves no capital by itself: it changes no account share, enables no config, and applying one to a bot that is already trading live re-sizes real risk — so that one asks for your PIN.

Every Candidate Seen
Before Any Order.

The entry path is cut in two: every bot proposes before anything executes. Turn the fleet pass on — it ships off, like every switch here that can reach an order — and one layer finally sees the whole tick at once. The desk ranks the candidates each bot has already cleared through its own gates, grades what that rule has really paid across five lanes of evidence, and prices every candidate by its marginal risk — what it adds to a book that already holds correlated positions, not what it would cost standing alone. Then it fills a risk budget the drawdown governor is allowed to cut. Its only power over a size is to shrink one.

Displaced is not discarded. The desk walks the bars the entry it refused would have lived through, prices the exit it would have found, and books the R it would have paid — so the desk is graded against the fleet it overruled, with the tie-breaks in that counterfactual deliberately set against the desk. A correlation it could not measure enters the arithmetic as zero and is written down as unmeasured, never quietly assumed away.

One Account.
Re-Split on Evidence.

With its pipeline running, the allocator proposes every few hours what share of the broker account each live pool should take — that switch ships off too, and none of this starts until somebody turns it on. The proposal comes from graded evidence, the brain's regime read, how many opportunities the scanner is actually finding, news risk, and the horizon prior — the last one capped low, because a structural view must never out-vote a measured one. A floor keeps a pool that is doing badly alive at a size that still produces evidence: a pool at nothing can never earn its way back. A ceiling stops one good week handing the account to one bot. A cap on daily movement stops the whole book chasing the morning.

A Machine That Argues
With Itself.

Above the signal engine sits a layer whose only job is to understand. It reads the platform's own state on a loop, writes down what it believes, invites its own agents to attack those beliefs, keeps what survives, and forgets the rest. Every claim carries a deadline, and every deadline is graded.

Six Brokers. One Adapter Pattern.

Every broker speaks the same duck-typed interface (ping · ticker · klines · order_book · market_order · account · balance). Routing per-symbol via the broker_router based on the instrument's asset_class. Encrypted credentials at rest (Fernet). Paper-mode default.

The Audit Trail Guards the Past.
The PIN Guards the Present.

A password gets you a session. It does not get you money. Every action that can move capital sits behind a second factor you hold, and a screen left unattended stops being a screen anyone can use.

Nothing Here Grades
Itself Kindly.

One rule runs under all of it. Every proposal is a gradable call with a deadline on it. Every plan is scored against the counterfactual — what actually happened, or what the trade it displaced would have paid. Anything unmeasured renders as an em dash, never as a zero dressed up as data. And every switch that can move money is off until a person turns it on, behind the PIN, with an audit row to show for it.

So here is the honest position, which is the better story anyway. The desk places no orders. It ranks, and its only power over a size is to shrink it; the allocator moves no share by itself. Both are built to run on every tick and every schedule, behind switches that ship off like every other switch here that can reach the money, and both are graded against what would have happened without them. Neither has been trusted with the account on this deployment. When one is, it will be because a human read the evidence and turned a switch — not because a landing page said they were ready.

Production-Hardened

Battle-tested OSS. Multi-stage Docker build, non-root runtime, ASGI worker for Channels. gunicorn + uvicorn serving HTTP and WebSockets; Sentry-instrumented; Celery beat for the recurring tasks; Channels for the per-user Eye push; a pg_dump nightly with rolling retention. The platform looks after itself.

Many Lenses. One Eye.

Each evaluator pulls from real data feeds (SEC, CFTC, FRED, news APIs, broker depth, etc.) and outputs a normalised score the scanner can compose. Add a new evaluator with one register_kind() call — the scanner picks it up automatically.