Invite-only access

Algorithmic and AI trading, built on your data, with nothing hidden from you.

Choose the market, the features and the algorithm. Tune the hyperparameters yourself and set what the model is rewarded for. Backtest it, run it on paper for as long as it takes to believe it, and promote it to real money only when you say so — one approved order at a time. The quant curriculum that teaches all of it ships with the platform.

Invite-only while we scale. Have a code? Sign in

We email you once, when your invite is ready. By joining you agree to our Terms and Privacy Policy.

3
model families — reinforcement learning, forecasting, sentiment
60s
evaluation cadence while a strategy is deployed
1Min–1Day
bar resolutions, US equities and crypto
Your strategy, in fullexample
{
  "name": "MA cross, RSI filter",
  "entryRules": [
    {
      "indicator":   { "type": "SMA", "params": { "period": 12 } },
      "operator":    "crosses_above",
      "compareWith": { "type": "SMA", "params": { "period": 26 } }
    },
    {
      "indicator": { "type": "RSI", "params": { "period": 14 } },
      "operator":  "less_than",
      "value":     70
    }
  ],
  "exitRules": [
    {
      "indicator":   { "type": "SMA", "params": { "period": 12 } },
      "operator":    "crosses_below",
      "compareWith": { "type": "SMA", "params": { "period": 26 } }
    }
  ],
  "entryCombine": "AND",
  "exitCombine":  "AND"
}
Frozen the moment you deploy — editing it later can't change a running strategy.
Why it did thatexample
  • 14:32:00evaluatedSMA(12) 2,481.10 crossed above SMA(26) 2,479.44 — entry conditions met
  • 14:32:01orderPaper buy 0.2014 ETH/USD at 2,481.55 — notional $500
  • 14:33:00evaluatedPosition open, exit conditions not met — holding
  • 15:07:00routeRegime changed trending → sideways, routed to "RSI Reversal"
  • 15:41:00haltDrawdown 2.6% exceeded your 2.5% limit — flattened, will not auto-restart

Two ways to trade

Write the rules yourself, or train a model to find them. Both run on the same engine.

Plenty of profitable strategies are a moving-average cross and a risk limit — you should not need a neural network to run one. And plenty of edges cannot be written down as a rule at all. Do either here, or run both side by side and let the backtests settle it.

Rules-based

Algorithmic trading

Classic systematic trading. Build the strategy yourself from indicators and conditions — no machine learning involved, and no training time.

  • ·PRICE, SMA, EMA, RSI, MACD, Bollinger bands, ATR
  • ·crosses_above · crosses_below · greater_than · less_than · equals
  • ·Combine entry and exit conditions with AND or OR
  • ·Validated on save, frozen on deploy, readable as plain JSON

Deterministic. You can trace exactly why it fired.

Machine learning

AI model trading

When the pattern is not something you can write down as a rule, train a model to find it on your data instead.

  • ·Reinforcement learning — PPO, A2C, SAC, TD3, DDPG
  • ·Price forecasting — LSTM, GRU, Transformer
  • ·Sentiment from news, social and filings
  • ·Your features, your hyperparameters, your reward weights

Adaptive. Learns behaviour you did not have to specify.

Both deploy the same way, inherit the same safety rails, and produce the same audit trail. The regime orchestrator can switch between them as the market changes — a rules strategy in chop, a trained model in a trend.

Full control

Your data, your features, your objective. No smart-defaults toggle standing between you and the model.

Most tools hand you a strategy and hide the machinery. This one hands you the machinery. Every item below is a parameter the trainer actually accepts.

Your data

Your symbols, your timeframes, your history depth. Datasets are versioned, so a result you liked stays reproducible.

Your features

Technical indicators, fundamentals, news sentiment, or a mix. If you think volume profile matters and momentum does not, build it that way.

Your architecture

Pick the algorithm, then tune it. Learning rate, batch size, steps, network shape — exposed, not buried behind a "smart defaults" toggle.

Your objective

Reinforcement rewards are weighted across four components — returns, downside, differential and Treynor — and you set the weights. Default is an even 25% split; tilt it toward downside if capital preservation matters more than upside.

Your risk limits

Maximum position concentration, reward scaling, and the drawdown at which a live deployment flattens and stays down.

Your artifacts

Trained models are yours. Keep them private to your account, publish them to the model zoo, or delete them outright.

Three families of model

Different questions need different models. Build one of each and let the backtest argue.

You are not picking a product tier here — you are picking a hypothesis about how your market works.

Reinforcement learning

An agent that learns a trading policy by trading — thousands of times over your history, keeping what paid.

PPOA2CSACTD3DDPG

You shape the reward: how much it should care about raw return versus downside risk, and how large a position it may ever hold.

Price forecasting

A sequence model that predicts where price goes next, from the features you decide are predictive.

LSTMGRUTransformer

You choose the architecture, the lookback window, the horizon, and which indicators become inputs.

Sentiment

A model that turns news and social text into a signal you can trade or use as a feature in another model.

NewsSocialFilings

You pick the sources and the window, and decide whether sentiment trades directly or feeds a price model.

Learn it while you build it

A full quant curriculum ships inside the platform. Three tracks, 27 modules, a quiz at the end of each.

Not a blog and not a video course bolted on for marketing. It teaches the things that actually decide whether a model survives contact with a market — and it is written by the people who built the engine you are pointing it at.

Financial Markets & Data

10 modules

  • ·Market Basics
  • ·Price Structures
  • ·Indicators (TA)
  • ·Feature Engineering
  • ·Data Hygiene
  • ·Risk & Reward
  • ·Market Regimes
  • ·Multi-Asset Mechanics
  • ·Execution & Slippage
  • ·Compliance & Ethics

Sentiment & Data Intelligence

8 modules

  • ·Text Data Basics
  • ·News Analytics
  • ·Social Media
  • ·Regulatory Docs
  • ·Cross-Modal Fusion
  • ·Sentiment Models
  • ·Temporal Dynamics
  • ·Bias & Manipulation

Machine Learning & Quant Engineering

9 modules

  • ·Data Prep & Splitting
  • ·Model Zoo Intro
  • ·Hyperparameters 101
  • ·Overfitting & Validation
  • ·RL Basics
  • ·RL Agents in Finance
  • ·LSTM/Sequence Models
  • ·Model Explainability
  • ·Model Deployment

The platform

Everything between a market hypothesis and a funded position.

No notebooks to babysit, no VPS to keep alive, and no scripting dialect invented for one vendor.

Dataset builder

Pull historical bars for a symbol and timeframe, stored as a versioned dataset with a market-regime label attached.

US equities and crypto · 1Min–1Day

Training on real GPUs

Reinforcement learning, price forecasting, or sentiment. Jobs bill per second of actual compute, and your tier includes an allowance — you see the estimate before it runs.

Serverless, per-second billing

Backtesting

Measured against history before it can touch an account, and segmentable by regime — so a strategy that only works in trends says so.

Regime-segmented

A rules engine you can read

Strategies are plain JSON. No black box, no scripting dialect invented for one vendor, and you can diff two versions.

Validated before deploy

Paper trading that runs itself

Deploy and the engine evaluates on every closed bar, places the order, tracks the position. Stocks park when the market closes and resume on their own; crypto runs around the clock.

Every 60 seconds

Live trading, on your say-so

Every real-money order waits for your approval — an SMS reply or a signed email link. Nothing fires while you sleep.

Hedge tier and above

Regime-aware routing

Map strategies to trending, sideways and volatile markets; the orchestrator classifies the live regime and routes accordingly, logging every switch.

Quant tier and above

Why it did that

Every evaluation, order, route change and halt writes an event with its reason.

Exportable event feed

How it works

Five steps, and you can stop at any of them.

Most users live at step four for a long time. That is the point — paper trading costs nothing but time, and time is what tells you whether a strategy is real.

  1. 01

    Build a dataset

    Choose a symbol and timeframe. Bars land as a versioned, regime-labelled dataset.

  2. 02

    Train a model

    Pick RL, forecasting or sentiment. Watch GPU progress and cost as the job runs.

  3. 03

    Backtest it

    Measure it against history before it can touch an account. Keep it or discard it.

  4. 04

    Deploy to paper

    The engine evaluates on every closed bar and places paper orders automatically.

  5. 05

    Go live, gated

    Promote it when you trust it. Each real-money order waits for your approval.

It stops itself

Breach your max-drawdown limit and the strategy flattens and stays down. It never restarts on its own.

It gives up on errors

Three consecutive failures and the deployment stops and tells you, instead of quietly retrying into a moving market.

Paper stays paper

Paper deployments are refused a live brokerage key outright, so a misconfiguration cannot spend real money.

Where we fit

Charting platforms show you the market. Signal services tell you what to do. We help you build the thing that decides.

An honest comparison — plenty of people are better served by one of the other three columns.

 CodonQuantSignal servicesDIY notebooksCharting platforms
Models you trained yourselfYesNoYesNo
GPU training includedYesNoBring your ownNo
Backtest → paper → live in one placeYesNoPartialPartial
Strategy frozen at deployYesNoNo
Per-order approval on real moneyYesNoNoNo
Decision-level audit trailYesNoBring your ownNo
Runs without your machine onYesYesNoPartial

We are built for one person in particular: you want your own models, trained on your own data, without also running your own GPU fleet, scheduler and execution plumbing.

Scope, stated plainly

What we cover, and where we drew the line.

Every platform makes these choices. Most leave you to discover them after you have paid, so here they are up front.

Built for a desk

The workbench is designed for a real screen — charts, backtests and training runs side by side. Live-order approvals come to your phone by SMS, so the time-critical part travels with you.

US equities and crypto

Two markets, covered properly: equities through the session calendar, crypto around the clock. Forex and options are outside our scope.

Your brokerage, your custody

Trading runs through your own Alpaca account. Your keys are encrypted at rest, and we never hold your funds or take discretion over them.

Access in waves

We onboard deliberately because we route real orders against real accounts. Joining the waitlist locks in founder pricing for when your invite lands.

Pricing

Pay for compute and live trading, not for seats.

Every plan includes the full workbench. What changes is how much you can train and whether real money is on the table. GPU hours beyond your allowance bill as metered usage — you see the estimate before a job runs.

Pioneer

Kick the tyres.

$0

  • ·3 model trainings
  • ·CPU training only
  • ·1 paper deployment
  • ·2 GB dataset storage

Included with your invite

Quant

For one serious strategy.

$29/mo

  • ·10 trainings · 10 GPU hours
  • ·3 paper deployments
  • ·Regime orchestrator
  • ·10 GB dataset storage

Hedge

First tier with real money.

$99/mo

  • ·50 trainings · 30 GPU hours
  • ·10 paper deployments
  • ·Live trading, 30 days
  • ·Private models

Institutional

Running a book.

$299/mo

  • ·200 trainings · 100 GPU hours
  • ·25 paper deployments
  • ·Live trading, 90 days
  • ·200 GB dataset storage

Running a desk and need more than Institutional? Tell us what you need — Enterprise is a conversation, not a checkout page.

Bring a hypothesis about a market. Leave with a model that has earned its position.

Access is invite-only while we scale the training fleet — join the waitlist and you keep founder pricing for life once your invite arrives. There is a feedback button on every screen in the app, and it reaches an engineer, not a ticket queue.

We email you once, when your invite is ready. By joining you agree to our Terms and Privacy Policy.

CodonQuant is software for building and running your own trading strategies. It is not investment advice, and we do not manage money or recommend trades. Automated trading can lose money, including more than you intended — backtested results describe the past and promise nothing. You connect your own brokerage account and you approve every live order.