A high-integrity trading architecture where hard rules pick the direction and an LLM-driven memory layer judges every execution—learning from every win and every scar.
Most "AI trading bots" are a webhook and a prompt. Cognitive Trader is a full agentic architecture — built so the LLM never decides direction, only learns from outcomes.
No ACT fires without signal alignment. The rules engine computes market_direction via sign(24h_change_pct) (threshold 1.5%) while the LLM provides thesis_confirmation. If trading_goal (0.50) isn't paired with market momentum (0.70), the Go-side gate blocks execution. Defense in depth.
W1: Manual fact extraction on trade close (source_channel='trade_outcome'). W2: Vector similarity retrieval via Ollama nomic-embed-text. The agent retrieves the 5 most-similar past trades into the prompt context. It doesn't just "remember"—it performs local RAG on its own historical scars.
A hard-coded circuit breaker in the cognitive_cycle. If 24h PnL (excluding pnl_unknown) breaches -$500, the system enters lockdown. It automatically cancels orphan STOP_MARKET and TAKE_PROFIT algo orders via the Binance API. No human cleanup required.
The ActionThreshold is dynamic (range 0.35–0.85). Every cycle, the lifecycle engine runs CalibrateFromOutcomes, adjusting weights based on a 30-day rolling PnL window. Realized profits tighten the threshold; the agent earns its right to be aggressive.
At 23:00 daily, the agent processes the day's internal_monologue and paper_trades. It generates dream_insights that are injected into the next day's working memory. This is where "curiosity-driven" parameters like intrinsic_motivation are calibrated offline.
In volatile regimes, anchoring on stale prices is fatal. If all prices in the market_stats feed are >45s old, the system enters Manage-Only mode. It will close or adjust existing positions but strictly blocks new opens. Real-world safety for live futures.
| Typical "AI trading" SaaS | Cognitive Trader | |
|---|---|---|
| Custody | Custodied or "read + trade" delegated. | Your keys. Never leave your machine. |
| Inference cost | Their cloud, per-call pricing. | Local LLM via Ollama (optional). SearXNG for news. Zero spend. |
| Decision logic | Black box. Strategy is "trust us." | Rules-engine direction. Source-readable supporting stack. |
| Fees | % of AUM or % of P&L. | Flat $129/yr early-adopter. No skim. |
There is a lot of dishonest marketing in algo trading. We'd rather lose the sale than oversell. Here's the straight version.
Most bots forget. Every cycle starts from zero — same indicators, same heuristics, same mistakes.
Cognitive Trader writes a short lesson at the end of every closed position: what the regime looked like, what the agent thought, what actually happened. Those lessons are indexed and fed back as context on the next decision. The bot doesn't just trade — it builds an internal book of what worked here last time.
This is the layer worth paying for.
Shorted ETHUSDT into a ranging regime on a "break of structure" that wasn't. ADX was below 18 the whole session. Don't trade trend-continuation logic when the classifier flags RANGING — wait for ADX > 22 or sit out. Next time this pattern shows in RANGING, skip.
Three things: the binary that does the work, the supporting stack it talks to, and the parts you bring yourself.
STAY_SILENT vs ACT decision cadence.-$500.nomic-embed-text embeddings and local model fallback.One JSON file per run. Fully versioned in git. Click a row to see the full breakdown — config, results, regime splits, and the honest notes on why it lived or died.
Early-adopter pricing — while we're still finding the bugs. Price goes up at 1.0.
Locks in $129/yr as long as you keep your subscription active. You're buying a seat on the build, not a finished product.
Software is provided as-is. You are responsible for your trades. Numbers above are hypothetical performance examples, not forecasts. Not financial advice.
Replace these four entries with the FAQ verbatim from the one-pager.
We're building in public. The Discord is where the work happens — strategy notes, regime-classifier tweaks, beta drops. Email comes later, once there's something to send.