Finance and accounting decision
Trading Wizard
A capable developer can build a narrow paper-bot + signal dashboard in about a week using existing open-source trading engines, but reproducing TradingWizard's Gemini analysis, MCP tool catalogue, polished UX, research desk and multi-market fleet at production scale is larger than a one-person project.
Visit website↗$39/mo
$468/yr
Read off the official pricing page.
$100one-off40 h to build
$200/mo6 h/mo upkeep
On cash alone, building overtakes the subscription at 6 seats.
Open-source builds that already do this
Every project below is open source and already does this job today. Fork one, self-host it, or take the parts you need - the build prompt further down assumes an empty file, and this is the shortcut past that. Licences differ; check the one on each card before you ship. All Trading Wizard alternatives, with the arithmetic →
What a replacement has to do
- Ingest live market prices, run strategy scans to detect setups, open/close simulated (paper) trades and record trade logs, surface signals and explanations via a web UI and a simple API for chat clients.
What it still won’t have
- Integrated Google Gemini reasoning layer and any proprietary LLM prompts/tuning
- Packaged Deep Research reports with cited multi-source institutional writing
- MCP tool catalog and plug‑and‑play AI-chat integration as a finished connector
- Mobile app and polished UX (iOS app experience and responsive polish)
- Aggregated global bot fleet, Bot Fund performance and community-driven feeds
What remains hard
- Product polish and ongoing maintenance
First-year cost
Keep paying
Paying is—cheaper in year one.
On cash alone, building overtakes the subscription at 6 seats.
Money you would actually spend
Time you would spend
—
What you would spend
What we assumed
The verdict above measures whether you could build it. This one is only about money.
Runnable build prompt
Build a minimal self-hosted TradingWizard-like service using Python (FastAPI) + Postgres + Redis + a lightweight JS frontend (React). Core features in scope: 1) ingest live prices for one asset class via a public market-data provider (websocket/REST) and store 1m candles, 2) implement a pluggable scanner that evaluates RSI and moving-average cross strategies and emits entry/stop/target, 3) implement a paper-trading engine that simulates positions, stop/target management and persists a trade timeline, 4) provide REST endpoints to list bots, get bot timeline, deploy/pause/delete a bot and to request a re-scan, 5) a simple dashboard to create one bot, view live price, timeline and trade log, 6) basic auth (single user) and background scheduler for periodic scans. Out of scope: multi-market support, paid billing, mobile app, LLM-based natural language explanations, MCP protocol, and premium research reports. Include error handling, input validation, unit tests for strategy logic and CI to run tests, and containerize the service for deployment (Docker Compose).
How we checked
How the score was reached
- Partly verdict base52
- An open-source build was found+5
- 5 cited sources+3
- Price verified on pricing page+3
- 3/3 assessment runs agreed+4
- Evidence score67
The base comes from the verdict. Everything under it is a check that either happened or did not, and each one is a fact frozen in this record rather than a judgement made at render time - so the same evidence always produces the same number.
How scoring works →Cited sources · 5
Every page the run actually retrieved.
- official productTradingWizard: AI that trades with you
- official pricingPricing | TradingWizard AI Pro and Ultimate Plans
- official docsWiz by TradingWizard and MCP Setup | TradingWizard Docs
- open sourcefreqtrade/freqtrade
- open sourceSuperalgos/Superalgos
Integrity checks
What held up, and what did not.
