A local-first algorithmic agent that learns from every position it closes — running on your own hardware, signing trades with keys that never leave the machine.
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 trade fires unless an active trading_goal AND a fresh market_direction signal both confirm. Prompt-side AND Go-side enforcement — defense in depth.
W1 extracts structured facts after every closed trade. W2 retrieves the 5 most-similar past trades into the next decision (pgvector). The bot remembers, not just trades.
ADX + volatility tags every cycle as TRENDING / RANGING / UNKNOWN. Momentum entries can be gated by regime so the bot pauses in chop instead of bleeding.
Hard 24h drawdown threshold (default −$500). Breach → lockdown, no new opens until reset. Not a stop-loss — a wallet-level circuit breaker.
The LLM never picks direction. sign(24h_change_pct) on the strongest mover does. The LLM reads past trades as context and vetoes — that's all. Transparent and auditable.
Yes — you also own the keys and the box. But this is table stakes, not the moat. It's listed last on purpose.
| 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.
Every backtest run, every verdict, shipped transparently. Full details on the backtest page.
| Run | Verdict | Net P&L | Sharpe | Trades |
|---|
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.