Agentic intelligence for your trading operations.

An entire trading desk, powered by AI — scalable cloud compute and optimisation algorithms searching, validating and deploying strategies at a scale no human desk could match.

  • Trading VPS
  • Native Python Strategies
  • Frontier Intelligence
Explore VC Trader

Illustration of a VC Trader session. The trader asks Agent Alpha to review FX and metals for the session, choosesClaude Opus 5.5 and sends the request. Agent Alpha reads the desk, the IC Markets MT5 account, the event calendar, live quotes and its research memory, briefs three helpers, reruns a gold strategy backtest in the cloud and charts XAUUSD with structure, a buy area, invalidation and a target, followed by a written analysis. The trader then asks it to place the trade; Agent Alpha refreshes the account and market, sizes and validates the order, and presents a buy-limit proposal awaiting the trader's approval. All figures are illustrative.

Illustrative Agent Alpha workflow, timing condensed

Trading ecosystem

  • Alpaca
  • Interactive Brokers
  • TradeStation
  • MetaTrader 5
  • Nasdaq
  • CME Group
  • NYSE
Explore VC Trader

The power of a trading desk. In one workspace.

A proprietary agentic harness purpose-built for trading operations. Coordinate specialist agents, define their workflows and connect research, market analysis and live execution in one continuous workspace.

Agents prepare and execute trades with swipe-to-confirm approval for agent-proposed orders.

  • Multi-agent orchestration
  • User-defined workflows
  • Alert-driven wakes
  • Agentic trade execution
  • Real market data
  • Shared research memory
  • Persistent workspace context
  • Purpose-built trading tools

Gold specialist

Active

XAUUSD · Claude Sonnet 5.5

Wakes every 5 min

AlertXAUUSD crosses 4,150

Instructions

Run on wake08:15 UTC
  1. Read situational awarenessbook · limits · events
  2. Read recent candlesXAUUSD · H1, H4
  3. Check the economic calendarUSD · high impact
  4. Assess and decidewith Technical Research
  5. Emit a signalto Agent Alpha

Agent Alpha · trade proposal

XAUUSD Buy limitIC Markets MT5 · demo

Entry
4,138.0
Stop
4,121.0
Target
4,182.0

0.05 lots · $85 at risk · 0.34%

Awaiting approval

Situational Awareness

Where market conditions meet operational intelligence.

VC Trader's proprietary Situational Awareness brings watched markets, multi-timeframe conditions, economic events, account exposure and recent decisions into a unified read. Your agents work with the state of the desk and the context around it.

  • Market regimes
  • Economic calendar
  • Cross-account exposure
  • Live account context
  • Multi-timeframe analysis
  • Decision history

Situational awareness

Liveas of 08:05 UTC

Book · 2 accounts

  • IC Markets MT5 · demoEURUSD long 0.10USD −10.9k
  • Prop account · MT5USDCHF short 0.20USD −20.0k

Same bet: both positions are short USD

computed from live positions and their currency legs

USD −30.9k

Calendar · USD

high impact

FOMC rate decision

Federal Reserve · in 2 days

Research · measured

EURUSD and USDCHF moved inversely on 86% of days

90-day window · research price store · a correlation, not a cause

Agent Alpha · observation

Your EURUSD long and USDCHF short are the same bet: both are short USD, about 30.9k combined. The FOMC decision is the next high-impact USD event.

Proposed Review combined USD exposure before the release.

Awaiting your review · nothing changed

Make informed decisions with connected knowledge

A semantic intelligence graph connects companies, markets, currencies, strategies, research, decisions and outcomes. Agents traverse those relationships to uncover hidden connections, retrieve relevant findings and bring accumulated knowledge into your trading desk.

  • IC Markets MT5 → exposed to → USD, through EURUSD → has leg → USD. Short USD 10.9k via EURUSD, computed from open positions · 08:05 UTC.
  • MTF_Breakout v7 → trades → XAUUSD, and → depends on → London open. 486 of 982 trades in the London session, from the strategy’s own trades · Jan ’24 → Jan ’25.
  • Research note (3 Oct) → about → XAUUSD, and → supersedes → the 18 Sep finding. Hold above 4,150 confirms trend, Technical Research · 3 Oct · source: walk-forward E-01HZX6A3.
  • Decision (buy limit approved) → acted on → XAUUSD, and → resulted in → trade closed +1.4R. Approved 5 Oct · closed at target, plan vs outcome joined on the order.
  • Desk watchlist → watches → NVDA → belongs to → Technology. NVDA → issuer of → earnings release → informs → AI & cloud demand research. Desk watchlist · 7 instruments, XAUUSD and six US technology names, grouped under Technology.
InstrumentEURUSDlong 0.10
USD
InstrumentXAUUSDGold · spot
StrategyMTF_Breakout v7
SessionLondon open
Research · 18 SepBreakouts fade into FOMC
Research · 3 OctHold above 4,150 confirms trend
DecisionBuy limit approvedby you · 5 Oct
TradeClosed +1.4Rtarget hit
WatchlistDesk watchlist7 instruments
ThemeTechnology
Connected researchAI & cloud demand
Live read

Short USD 10.9k via EURUSD

computed from open positions · 08:05 UTC

Measured

486 of 982 trades in the London session

from the strategy’s own trades · Jan ’24 → Jan ’25

Research note

Hold above 4,150 confirms trend

Technical Research · 3 Oct · source: walk-forward E-01HZX6A3

Decision ledger

Approved 5 Oct · closed at target

plan vs outcome joined on the order

Watchlist

Desk watchlist · 7 instruments

XAUUSD and six US technology names, grouped under Technology

Company intelligence

Meta · evidence connected

Earnings call → AI & cloud demand research

METASource documentResearch
Company intelligence

Apple · evidence connected

Form 10-K → AI & cloud demand research

AAPLSource documentResearch
Company intelligence

NVIDIA · evidence connected

Earnings release → AI & cloud demand research

NVDASource documentResearch
Company intelligence

Microsoft · evidence connected

Investor update → AI & cloud demand research

MSFTSource documentResearch
Company intelligence

Amazon · evidence connected

Earnings release → AI & cloud demand research

AMZNSource documentResearch
Company intelligence

Alphabet · evidence connected

Form 10-K → AI & cloud demand research

GOOGLSource documentResearch
USD
exposed to ↑has leg ↑
InstrumentEURUSDlong 0.10
Live read

Short USD 10.9k via EURUSD

computed from open positions · 08:05 UTC

StrategyMTF_Breakout v7
tradesdepends on
InstrumentXAUUSDGold · spot
SessionLondon open
Measured

486 of 982 trades in the London session

from the strategy’s own trades · Jan ’24 → Jan ’25

Research · 3 OctHold above 4,150 confirms trend
aboutsupersedes
InstrumentXAUUSDGold · spot
Research · 18 SepBreakouts fade into FOMC
Research note

Hold above 4,150 confirms trend

Technical Research · 3 Oct · source: walk-forward E-01HZX6A3

DecisionBuy limit approvedby you · 5 Oct
acted onresulted in
InstrumentXAUUSDGold · spot
TradeClosed +1.4Rtarget hit
Decision ledger

Approved 5 Oct · closed at target

plan vs outcome joined on the order

NVDA
watches ↑belongs to
WatchlistDesk watchlist7 instruments
ThemeTechnology
Watchlist

Desk watchlist · 7 instruments

XAUUSD and six US technology names, grouped under Technology

META
watches ↑issuer of
WatchlistDesk watchlist7 instruments
META · transcriptEarnings call
Company intelligence

Meta · evidence connected

Earnings call → AI & cloud demand research

METASource documentResearch
AAPL
watches ↑issuer of
WatchlistDesk watchlist7 instruments
AAPL · filingForm 10-K
Company intelligence

Apple · evidence connected

Form 10-K → AI & cloud demand research

AAPLSource documentResearch
NVDA
watches ↑issuer of
WatchlistDesk watchlist7 instruments
NVDA · releaseEarnings release
Company intelligence

NVIDIA · evidence connected

Earnings release → AI & cloud demand research

NVDASource documentResearch
MSFT
watches ↑issuer of
WatchlistDesk watchlist7 instruments
MSFT · newsInvestor update
Company intelligence

Microsoft · evidence connected

Investor update → AI & cloud demand research

MSFTSource documentResearch
AMZN
watches ↑issuer of
WatchlistDesk watchlist7 instruments
AMZN · releaseEarnings release
Company intelligence

Amazon · evidence connected

Earnings release → AI & cloud demand research

AMZNSource documentResearch
GOOGL
watches ↑issuer of
WatchlistDesk watchlist7 instruments
GOOGL · filingForm 10-K
Company intelligence

Alphabet · evidence connected

Form 10-K → AI & cloud demand research

GOOGLSource documentResearch

Research note (3 Oct) → about → XAUUSD, and → supersedes → the 18 Sep finding

Deep analytics across accounts & backtests

Explore performance, understand risk and examine strategy robustness with account analytics, backtest reports and walk-forward diagnostics—all in one workspace.

  • Monthly returns

    Strategy report · 2025

    1. Jan+0.2%
    2. Feb+2.0%
    3. Mar+2.8%
    4. Apr+2.8%
    5. May−0.8%
    6. Jun−3.9%
    7. Jul−1.6%
    8. Aug+2.8%
    9. Sep+5.2%
    10. Oct−1.9%
    11. Nov+5.1%
    12. Dec+4.0%

    Year 2025+16.7%

  • Strategy report

    Backtest · 1.0 year

    Total return
    +16.7%
    Max drawdown
    11.8%
    Sharpe ratio
    2.02
    Profit factor
    1.74
    Win rate
    61.2%
    Total trades
    982
  • Activity

    Account · UTC

  • Performance by weekday

    Account analytics

    Loss ◂ P&L ▸ ProfitNet P&LTradesWin %Mon−$4563148%Tue+$1.2k3959%Wed+$9042357%Thu−$222850%Fri−$1.5k3142%
  • Long vs short

    Account analytics

    Long 62%Short 38%
    TradesNet P&LLong2662%−$1.4kShort1638%+$530
  • Trades by symbol

    Account analytics

    • US3014
    • GBP_USD11
    • EUR_USD9
    • XAU_USD8
  • Evaluation score cloud

    Walk-forward · Window 1 · 200 evaluations

    Train → test +18.40% / +14.20%Test Sharpe 1.71

CMA-ES search

Running

MTF_Breakout v8 candidate · XAUUSD H1

AWS research compute · fill model: tick-accurate

Generation 14 / 2010 candidates / gen
Best score 38.42Mean 31.0

atr_mult · breakout_len · session_filter

session_edge.ipynb

Python 3 · idle
[3]
import pandas as pd

oos = pd.read_parquet("oos_trades.parquet")

by_session = (
    oos.groupby("session")["r_multiple"]
       .agg(trades="count", mean_r="mean",
            win_rate=lambda r: (r > 0).mean())
       .round(2)
)
by_session
by_session = oos.groupby("session")
by_session["r_multiple"].agg(
    trades="count", mean_r="mean"
).round(2)
Out
sessiontradesmean_rwin_rate
Asia212-0.040.46
London4860.210.58
New York2840.090.53

Rolling walk-forward

4 windows · Jan ’24 → Jan ’25
  • W1+0.16R
  • W2+0.22R
  • W3−0.03R
  • W4searching

Train (in-sample) Test (out-of-sample)

Quant Research

Build strategies. Test their limits.

Bring strategy development, custom analysis and large-scale experimentation into one environment. Develop in Python, test with tick-level precision, and put scalable cloud compute behind parameter optimisation and deeper analysis of your results.

  • Jupyter & Python
  • AWS research compute
  • Tick-accurate backtesting
  • Fast vectorised backtesting
  • CMA-ES optimisation
  • Rolling walk-forward
  • Parameter optimisation

Cloud Deployment

Managed infrastructure for live trading operations.

A scalable hosting environment for your trading operations. Run Python strategies on managed Linux infrastructure, maintain secure connections to your brokers and host Windows MT5 terminals where needed—bringing strategy deployment, account connectivity and operational oversight into one workspace.

  • Managed AWS research compute
  • Linux strategy hosting
  • Windows MT5 terminals
  • Continuous cloud execution

Customer-approved Python strategies trade automatically. Orders an agent proposes still wait for your confirmation.

MTF_Breakout v7

Deployed 3 Oct · Python strategy

Live
  • XAU/USD
  • EUR/USD
  • US30
Account
IC Markets MT5 · demo
Execution
Automatic · approved by you
Risk / trade
0.40%
Host
running · linux-strategy-01
VC Trader account strategy deployments, showing London ORB and Gold Scalper strategies.

A trading desk governed by your rules.

Turn your risk rules into operational controls. Set account limits, monitor exposure across deployments and check orders before execution. Combine circuit breakers and a kill switch with detailed analytics and a trading journal to oversee activity and intervene when needed.

  • Account risk limits
  • Execution risk gate
  • Exposure oversight
  • Analytics & journal

Kill switchHalts trading and flattens all positions

Account limits

Max daily loss
$1,738.83
Risk per trade
5%
Max open positions
25

Risk gate · pre-trade check

XAUUSD buy limit · 0.05 lots · stop 4,121.0

  • Risk per trade$85 ≤ 5% limit
  • Daily loss room$85 of $1,738.83
  • Stop-loss attached4,121.0
  • Open positions3 of 25 after fill
  • Currency exposureadds to USD short

Within your limits · awaiting your approval

Trading journal

  • 5 Oct 09:16XAUUSD buy limit 0.05checks passed · awaiting you
  • 4 Oct 15:02XAUUSD sell 0.05closed +0.6R · note added
  • 3 Oct 11:40GBPUSD long 0.40refused · no stop-loss attached

Models & BYOK

Choose the intelligence behind your desk.

Our proprietary Harness turns model intelligence into a connected trading desk, equipping agents with research and execution tools, configurable workflows and live operational context. Through the knowledge graph, they retrieve prior findings, follow relationships and build on the accumulated knowledge of your operation.

  • Model-agnostic harness
  • Frontier model choice
  • Bring your own key

Model · Agent Alpha

BYOK

Anthropic

  • Claude Fable 5.1
  • Claude Opus 5.5
  • Claude Sonnet 5.5
  • Claude Haiku 4.5

Google

  • Gemini 3.1 Pro Preview
  • Gemini 2.5 Pro

DeepSeek

  • DeepSeek V4.1 Flash
Your Anthropic keyconnected · key hidden

Same harness: tools, workflows and workspace context

FAQs

Questions about VC Trader.

What can VC Trader's agents do?

They can research markets, coordinate specialists, develop and test strategies, monitor your workspace and prepare trades for live execution. Agent-proposed trades require swipe-to-confirm approval.

Do I need to write Python?

You can work with agents to author Python strategies, or write and investigate them yourself in Jupyter. The research environment supports both approaches.

How does the intelligence graph support trading research?

It connects research to instruments, strategies, decisions and outcomes through semantic relationships. Agents can retrieve relevant findings and carry context between investigations.

What research can I run in the cloud?

Tick-accurate backtests, CMA-ES parameter searches and rolling walk-forward evaluation, alongside Python analysis in Jupyter notebooks.

Can deployed strategies trade automatically?

Yes. Customer-approved Python strategies can execute automatically on connected MT5 accounts through cloud hosting. Agent-proposed orders require your confirmation.

Can I choose the AI model and use my own key?

Yes. VC Trader supports model choice and BYOK within the same agentic harness and workspace.

Build your trading operation with VC Trader.

Explore the platform through paid early access.

Apply for early access