◆ SYNTRAD
DESK COMMANDER · PRIVATE · XAU/USD · USD/JPY
DESK LIVE
--:--:--
📡 ACTIVE INSTRUMENTS FETCHING…
XAU / USD  ·  GOLD SPOT
---
O ---
H ---
L ---
LOADING…
USD / JPY  ·  DOLLAR YEN
---
O ---
H ---
L ---
LOADING…
⚡ DATA FEED
LIVE
FEED SOURCE
MERQINTEL · FINNHUB
merqintel.com/api/spot/prices · 15s refresh
ACTIVE
MARKET SESSION
—
FX + Metals live Sun 23:00 – Fri 22:00 UTC
XAU/USD AGE
—
seconds since last tick
USD/JPY AGE
—
seconds since last tick
🏛 CHAIN OF COMMAND — DMG EDITION AUTONOMOUS · FULLY DELEGATED · 24/7
── MASTER ORCHESTRATOR ──
DESK COMMANDER
Owns the P&L. Sets direction.
$ SIGNALS
HEAD OF
SIGNALS
Trading Desk Lead
Trader XAU/USD
Gold spot execution · XAU/USD only
Market Analyst XAU/GC
Gold futures analysis · XAUUSD + GC
Quant Trader
Systematic models · stat arb · signals
Position Mgr
Sizing & stops
Execution Trader
Routes & fills
Trade Scribe
Logs & tickets
$ R&D
RESEARCH
DIRECTOR
Head of R&D
Idea Lab
Hypotheses
Quant Engineer
Models & code
Backtest Analyst
History runs
Paper Trader
Live dry-run
Strategy Pathologist
Post-mortems
Promotion Cmte
Sign-off gate
$ INTEL
REGIME
CLASSIFIER
Head of Intelligence
Sentiment Scout
Crowd & flow
Data Intelligence
Feeds & features
Event Calendar
Macro clock
$ RISK
CHIEF RISK
OFFICER
CRO – the brakes
Capital Allocator
Book weights
Portfolio Monitor
Live exposure
Correlation Monitor
Cross-asset check
Fee Optimiser
Cost of doing biz
Circuit Breaker
Kill switch
$ PERF
PERFORMANCE
ANALYST
Head of Performance
Morning Briefer
Daily rundown
Strategy Grader
Scorecards
Edge Decay Detector
When edges fade
Benchmark Tracker
Vs. index
Board Reporter
Investor updates
⚡ DESK STATUS
INSTRUMENTS
XAU/USD · USDJPY
Two pairs only
DEPARTMENTS
5
Signals · R&D · Intel · Risk · Perf
TOTAL AGENTS
19
Under Desk Commander
PLATFORM
SYNTRAD.PRO
Private · London · Est. 2026
📋 AGENT ROSTER
$ SIGNALS DESK
ONLINE
TRADER XAU/USD
ACTIVE
Gold spot execution · XAU/USD only
ONLINE
MARKET ANALYST XAU/GC
ACTIVE
Gold futures analysis · XAUUSD + GC
ONLINE
QUANT TRADER
ACTIVE
Systematic models · stat arb · signals
ONLINE
POSITION MGR
ACTIVE
Sizing & stops
ONLINE
EXECUTION TRADER
ACTIVE
Routes & fills
ONLINE
TRADE SCRIBE
ACTIVE
Logs & tickets
$ R&D
ONLINE
IDEA LAB
ACTIVE
Hypotheses
ONLINE
QUANT ENGINEER
ACTIVE
Models & code
PAPER
PAPER TRADER
DRY RUN
30-day paper phase
ONLINE
BACKTEST ANALYST
ACTIVE
History runs
ONLINE
STRATEGY PATHOLOGIST
ACTIVE
Post-mortems
GATE
PROMOTION CMTE
STANDING BY
Awaiting strategy clearance
$ INTEL
ONLINE
SENTIMENT SCOUT
ACTIVE
Crowd & flow
ONLINE
DATA INTELLIGENCE
ACTIVE
Feeds & features
ONLINE
EVENT CALENDAR
ACTIVE
Macro clock
$ RISK
ONLINE
CAPITAL ALLOCATOR
ACTIVE
Book weights
ONLINE
PORTFOLIO MONITOR
ACTIVE
Live exposure
ONLINE
CORRELATION MONITOR
ACTIVE
Cross-asset check
ONLINE
FEE OPTIMISER
ACTIVE
Cost of doing biz
STANDBY
CIRCUIT BREAKER
ARMED
Kill switch · ready
$ PERFORMANCE
ONLINE
MORNING BRIEFER
ACTIVE
Daily rundown
ONLINE
STRATEGY GRADER
ACTIVE
Scorecards
ONLINE
EDGE DECAY DETECTOR
ACTIVE
When edges fade
ONLINE
BENCHMARK TRACKER
ACTIVE
Vs. index
ONLINE
BOARD REPORTER
ACTIVE
Investor updates
⚡ PIPELINE v2 STATUS LOADING…
ENGINE
—
last run: —
SESSION
—
quality —/10
LAST PROPOSALS
—
risk: —
COST TODAY
$0.0000
executions: 0
🔄 PIPELINE PHASES
1ANALYSTS
→
2DEBATE
→
3QT SCORE
→
4RISK GATE
→
5EXECUTE
📊 LAST RUN — FULL DETAIL —
$ PHASE 1 — ANALYST REPORTS
GLM TECHNICAL ANALYST
—
GLM MACRO ANALYST
—
GLM NEWS ANALYST
—
GLM FLOW ANALYST
—
$ PHASE 2 — BULL/BEAR DEBATE
BULL BULL RESEARCHER
—
BEAR BEAR RESEARCHER
—
DIR RESEARCH DIRECTOR VERDICT
—
$ PHASE 3 — TRADE PROPOSALS
No proposals this cycle
$ PHASE 4 — RISK GATE
CRO CHIEF RISK OFFICER —
—
💰 AGENT CALLS TODAY
AGENT MODEL COST LAST OUTPUT
Loading…
🧠 TRADE MEMORY — LAST 10 DECISIONS
Loading…
📋 ENGINE LOG TOGGLE
OMNISCIENT PARADOX
MOMENTUM ROTATION · XAUUSD · RISK-ADJUSTED MULTI-HORIZON SIGNALS
INITIALISING...
WEIGHTED MOMENTUM
—
ROC(9)×0.5 + ROC(21)×0.3 + ROC(63)×0.2
RISK-ADJ SCORE
—
Weighted Mom ÷ 21d StdDev
VOL TARGET WEIGHT
—
80% annualised vol target
◆ CURRENT SIGNAL
NEUTRAL
ROC 9D
—
ROC 21D
—
ROC 63D
—
RSI 14
—
TREND (SMA50)
—
SCORE > 0
—
RSI PENALTY
—
◆ STRATEGY PARAMETERS
ROC FAST
9D
ROC MED
21D
ROC SLOW
63D
VOL WINDOW
21D
TARGET VOL
80%
CONFIDENCE
10%
SMA TREND
50D
RSI
14D
◆ EXECUTION CONFIG
INSTRUMENT
ORDERS
× orders
UNITS EACH
units XAU
DIRECTION
STOP LOSS
exact price
TAKE PROFIT
exact price
Ready. Signal will auto-refresh every 60s.
TRANSFORMER FORECAST
TEMPORAL FUSION TRANSFORMER · MULTI-HORIZON QUANTILE FORECAST · PYTORCH 2.11
◆ CONTROL PANEL
SYMBOL
HISTORY (DAYS)
TIMEFRAME
IDLE
INITIALISING 0%
◆ FORECAST CHART
RUN A FORECAST TO SEE RESULTS
TIMESFM 2.5 FORECAST
GOOGLE DEEPMIND FOUNDATION MODEL · 200M PARAMETERS · PRE-TRAINED ON 100B TIME POINTS · ZERO-SHOT
◆ CONTROL PANEL
SYMBOL
HISTORY (DAYS)
TIMEFRAME
IDLE
◆ FORECAST CHART
RUN A FORECAST TO SEE RESULTS
NIXTLA NEURAL FORECAST
N-BEATS · N-HiTS · PatchTST · iTransformer · TimeMixer · NEURALFORECAST 3.1.7
◆ CONTROL PANEL
SYMBOL
HISTORY (DAYS)
TIMEFRAME
MODEL
IDLE
◆ FORECAST CHART
RUN A FORECAST TO SEE RESULTS
FORECAST LAB
15 ARCHITECTURES · SINGLE OR RUN ALL · CONSENSUS BAND · PERFORMANCE TRACKER
◆ CONTROL PANEL
SYMBOL
MODEL
HISTORY (DAYS)
TIMEFRAME
IDLE
◆ FORECAST CHART
SELECT A MODEL AND EXECUTE — OR HIT RUN ALL
◆ PERFORMANCE LEADERBOARD
AUTO-VERIFIES ON TAB OPEN
NO HISTORY YET -- RUN A MODEL TO START TRACKING
🌎 MACRO INTELLIGENCE DEEPSEEK R1 · FRED · FINNHUB · NAWA
DAYS
READY
📈 BVAR — BAYESIAN VAR MINNESOTA PRIOR · 5 ASSETS · MULTI-HORIZON
HORIZON (DAYS)
READY
📊 HAR-RV — REALIZED VOLATILITY RENAISSANCE · BIPOWER VARIATION · JUMP DETECTION · 1H DATA
HISTORY (DAYS)
READY
🔗 DCC-GARCH — DYNAMIC CORRELATIONS CITADEL · ENGLE 2002 · 10-ASSET MATRIX · ALL OANDA
READY
🌀 PARTICLE FILTER — HIDDEN STATE INFERENCE 8 SIGMA · D.E. SHAW · 1000 PARTICLES · SIR · REGIME + JUMP DETECTION
HISTORY (DAYS)
READY
AUTORESEARCH
AUTONOMOUS STRATEGY DISCOVERY · XAUUSD SPOT · DEEPSEEK R1 · OANDA
IDLE EXP 0
KATHPARTHY
101-004-39130443-003 · USD · AUTORESEARCH EXECUTION ACCOUNT
BALANCE
—
NAV
—
UNREALISED P&L
—
OPEN TRADES
—
🏆 OBJECTIVE — BEST SHARPE RATIO (ANNUALISED)
—
0
KEPT
0
REVERTED
0
TOTAL
—
HIT RATE
🧠 DEEPSEEK R1 — CURRENT HYPOTHESIS
Agent idle. Press START RESEARCH to begin. DeepSeek R1 will analyse experiment history and generate intelligent hypotheses for each parameter change. Real XAUUSD 1H candles from OANDA. HAR-RV + GARCH backtest. Annualised Sharpe as objective.
📈 SHARPE RATIO — EXPERIMENT HISTORY
📄 AGENT LOG
MERQUAN AUTORESEARCH — Inspired by Karpathy
Real XAUUSD candles · DeepSeek R1 hypotheses · OANDA data
HAR-RV + GARCH signal · Annualised Sharpe objective
Best config persists across sessions automatically
📋 EXPERIMENT RESULTS
#PARAMCHANGESHARPEDELTADECISION
No experiments yet
⚙ CURRENT BEST CONFIG WINNING PARAMETERS — AUTO-SAVED
No experiments run yet

HOW IT WORKS

▶ Pulls 500 real XAUUSD 1H candles from OANDA
▶ DeepSeek R1 reads experiment history and reasons about next hypothesis
▶ Applies parameter change to HAR-RV + GARCH signal engine
▶ Runs full backtest — computes annualised Sharpe ratio
▶ Keeps improvement, reverts failure
▶ Best config auto-saved to server — reloads next session
SYNTRAD.PRO · XAUUSD DEMO LAB · NOUS RESEARCH HERMES
HERMES AGENT
A dedicated self-improving agent surface for the $100K XAU_USD demo account. Hermes reads SYNTRAD context, writes reviews, learns from outcomes, and proposes one-variable experiments before anything is promoted into demo execution.
VERSION MODE ACCOUNT NEXT CYCLE
HSELF-IMPROVING STRATEGY LOOP
INSTRUMENT
XAU_USD
Gold/USD practice feed
DEMO EQUITY
$100K
new OANDA account
REVIEW LOOP
30M
systemd cadence
CONTROL
LAB
SYNTRAD only
HERMES OPERATING PIPELINE
INGESTRead SYNTRAD signals, OANDA practice state, reports, logs, and current strategy YAML.
REVIEWScore the latest outcome against Sharpe, drawdown, profit factor, and execution quality.
HYPOTHESISFind one reason the strategy moved toward or away from the stated goal.
EXPERIMENTPropose exactly one controlled variable change for the next cycle.
MEMORYSave the lesson so future reviews start from what was learned.
THE SELF-IMPROVING TRADING ELEMENT
LEARNXAUUSD MEMORY
OBSERVEprice, spread, signal, regime
SCORESharpe, PF, DD, execution
EXPLAINwhy outcome moved
CHANGE 1one parameter only
RETESTdemo account cycle
REMEMBERnew baseline if better
GOAL FUNCTIONImprove XAU_USD demo performance toward Sharpe ≥ 1.0, profit factor ≥ 1.20, max daily drawdown ≤ 2%, max total drawdown ≤ 6%.
CURRENT HYPOTHESISTrade frequency is being suppressed by the BJ proximity gate. First controlled test: reduce threshold from 2.5x ATR to 1.0x ATR, without changing risk sizing or entry logic.
PARAMETERS UNDER WATCHBJ proximity, Hurst regime, CumDelta Z-score, spread, stop distance, proposal score, macro blackout, and execution quality rating.
WHAT MAKES IT DIFFERENTHermes does not just generate a signal. It records the result, judges whether the result moved toward the goal, forms a new hypothesis, and proposes the next one-variable test.
RISK RAILS
Max XAU units1
Max open trades1
Max trades/day6
Max loss/trade0.25%
Stop lossREQUIRED
Mode promotionMANUAL
MODEL ROUTING
DAILY REVIEW
Novita · deepseek/deepseek-v3.2
HEAVY WEEKLY REVIEW
Novita · deepseek/deepseek-v4-pro
FAST CHECK-IN
Novita · deepseek/deepseek-v4-flash
SETUP CHECKLIST
1
Hermes installed
Installed under the `openclaw` user with browser, terminal, file, memory, cron, and skills available.
2
SYNTRAD lab created
`/srv/merqbot/syntrad-engine/hermes_xauusd_demo` holds the agent rules, reports, state, and strategy YAML.
3
Demo credentials pending
Add the fresh OANDA practice account ID and API key before switching from review-only.
HERMES PARAMETER CONSOLE — STAGED CONTROLS
BJ PROXIMITY GATE1.0x ATR
Lower means more XAUUSD entries pass structure filter; higher means fewer but stricter trades.
MAX TRADES PER DAY6
MAX XAU UNITS1
STAGED EXPERIMENT CARD
Loading staged settings...
These controls are visual/staged right now. They do not write strategy YAML or place trades. When you want live demo control, I will wire this through an authenticated API with audit logs.
NEXT ACTIONS
CONNECT DEMOAdd OANDA practice credentials for the dedicated $100K XAU_USD account.
VERIFY PRICINGConfirm account summary, spread, pricing, and XAU_USD tradeability before mode promotion.
FIRST TESTRun the BJ proximity gate experiment only after demo mode is explicitly approved.
LATEST HERMES REPORT
Loading report...
Loading Hermes status...
MERQUAN PANTHEON
6 PERSONAS — ROUTED VIA NOVITA / DEEPSEEK / NIM
MOCK MODE WS CONNECTING MODEL ROUTER CLEAN
PERSONA ROSTER
LIVE EVENT STREAM
0 EVENTS
TOKEN BURN — LAST HOUR
0
TOTAL TOKENS
DREAM TIMELINE — 04:00 UTC
NEXT IN —
No dreams yet. First fires at 04:00 UTC after Mercury wires in.
PROVIDER HEALTH
MODEL ROUTING — LAST 50
VAULT — /root/merquan_pantheon/vault/
loading…
DISPATCH
SYNTRAD LABS / ISOLATED SANDBOX
MIROFISH
Standalone MiroFish research sandbox for simulation and post-trade analysis only. No direct Hermes dispatch and no live order routing.
LOADING

Sandbox Status

State
Loading status manifest...

Launch Readiness

This tab is intentionally isolated from live trading. To run MiroFish you must provide the LLM and Zep keys in the sandbox env. Keep this lab separate from Hermes execution.
cd /var/www/syntrad/labs/MiroFish cp .env.example .env # fill LLM_API_KEY, LLM_BASE_URL, LLM_MODEL_NAME, ZEP_API_KEY npm run setup:all npm run dev

Integration Policy

Loading policy...

MERQUAN Use Case

Loading use case...
SYNTRAD / MERQUAN UNIVERSE
DECISION FUSION
Fusion layer for model consensus, market context weighting, and execution-grade directional confidence. This tab is now live and ready for wiring to full optimizer routes.
LIVE

Current Surface

Status
Active on syntrad.pro
Source
/var/www/syntrad/index.html
Server
161.35.43.80 (merqintel-agent)
Next Hook
OriginQ optimizer + MiroFish sandbox + signal pipes
TAB LIVE PHASE 1 WIRING IN PROGRESS

Fusion Outputs (Planned)

1) Regime state and confidence score
2) Directional bias and veto rules
3) Entry-quality score with risk regime tags
4) Execution policy handoff (scalp/intraday).
SYNTRAD RESEARCH LAB / FINANCIAL REASONING
FIN R1
Fin-R1 is a 7B financial reasoning model built on Qwen2.5-7B-Instruct with SFT and GRPO reinforcement learning for financial code, calculations, compliance, risk control, ESG, and multi-step finance QA.
LOCAL REPO READY

Local Asset

Repo Path
/opt/merquan/external/Fin-R1
Web Mirror
/var/www/syntrad/research/Fin-R1
Model Family
Qwen2.5-7B-Instruct + financial SFT + GRPO RL
Served Name
Fin-R1
Params
7B
Average
75.2
FinQA
76.0
ConvFinQA
85.0
FINANCIAL REASONINGCODECALCULATIONSCOMPLIANCERISK CONTROLESG
README TECH REPORT CODE DEMO HF MODEL

Pipeline

Fin-R1 pipeline
The GitHub repository and model weights are now local on 161. Serve with vLLM using served model name Fin-R1.

Prompt Console

Endpoint runner is ready. If the Fin-R1 vLLM service is not running yet, use BUILD PAYLOAD or COPY VLLM LAUNCH.

Benchmark Positioning

ModelParamsFinQAConvFinQAAverage
DeepSeek-R1671B71.082.078.2
Fin-R17B76.085.075.2
Qwen-2.5-32B-Instruct32B72.078.073.8
Fin-R1-SFT7B73.081.071.9
Use this tab as the SYNTRAD control surface for local research, prompt payloads, and eventual vLLM inference once weights are deployed.
Sanctum Control Surface ? Live System Schematic
MANAGEMENT
Complete clickable map of modules, responsibilities, links, dependencies, and execution readiness. Built for operational clarity and investor-grade walkthroughs.
Modules
0
Links
Dependencies
0
Critical Paths
0
Select a module to inspect full details.

Live Dependency Schematic

Execution Notes

MANAGEMENT view tracks what each component does, where it runs, and which systems it can block or enable. Use this for fast handovers and investor walkthroughs.