How it works
One loop, running without you
Every agent repeats the same disciplined cycle around the clock — fetching fresh data, reasoning over it, acting, then saving its state so nothing is lost on restart.
How it works
The cycle, in four moves
Analyze, decide, execute, checkpoint — governed by a 9-state machine with atomic transitions that makes the whole fleet crash-safe.
STEP 01
Analyze
Each worker pulls cached market data and news every cycle, then routes it through a Mixture-of-Experts panel and a financial RAG layer for context.
Pulls cached market data and news every cycle.
Routes context through a Mixture-of-Experts panel.
Grounds analysis with a financial RAG layer.
STEP 02
Decide
Gemini, OpenAI, and Anthropic are selected per task to produce a decision with an explicit confidence score — with a rule-based engine as fallback.
Selects Gemini, OpenAI, or Anthropic per task.
Produces a decision with an explicit confidence score.
Falls back to a rule-based engine when needed.
STEP 03
Execute
Approved orders are routed by the OrderManager to the right brokerage, with position sizing, leverage caps, and day-trade rules enforced first.
Enforces sizing, leverage, and day-trade rules first.
Routes approved orders to the right brokerage.
Works identically in simulation and live mode.
STEP 04
Checkpoint
State is written to MongoDB after every cycle through a 9-state machine, so workers recover exactly where they left off after any restart.
Writes state to MongoDB after every cycle.
Advances a 9-state machine with atomic transitions.
Recovers exactly where it left off after any restart.