Feature Overview
What each module does and when to use it, so you can quickly tell which capability fits your scenario.
AI Agent
Features: Single entry point; via conversation you can trigger strategy lookup, backtest, analysis, parameter tuning, risk suggestions, etc.; while running you can have the AI analyze performance or adjust the strategy directly.
Use case: No need to jump between pages; use natural language to check strategies, run backtests, view performance, change parameters; good for quick idea validation and daily review and optimization.
Monitoring and Alerts
Features: run status and health checks, execution logs and audit, multi-channel notifications and alerts (Telegram, email, Webhook group bots, etc.).
Use case: know at any time whether the system and bots are healthy, whether orders are being executed, and whether anything looks off; get alerts when something goes wrong for quick diagnosis and intervention.
Strategy and Backtest
Features: visual configuration of buy / long & sell / short conditions and indicators, multiple timeframes and templates, "strategy + execution config" backtests over historical K-lines as tasks, per-pair reports, and reusable signals and indicators.
Use case: build strategies and execution configs without code, then validate returns and risk on historical data before going to paper or live.
Risk Management
Features: two-layer risk control—per-pair execution config (stops, targets, profit protection, position, max drawdown, scale-in, consecutive-loss management, etc.) + bot-level safety net (overall TP / SL, default leverage).
Use case: cap per-trade or overall losses, control position and drawdown, and automatically protect capital when a strategy fails or the market behaves abnormally.
Trading Execution
Features: spot and futures order placement, order and position sync, multi-exchange connectivity and rate limiting; trading bots support Paper Trading and Live Trading.
Use case: produce buy / sell signals from the strategy and auto-place orders and manage positions per the per-pair execution config; validate behavior in paper first, then switch to live with real capital.
AI-Driven Trading
Features: runs inside the system's trading framework with traceable signals and decisions; trading signals come straight from the AI's analysis, while the platform's risk controls are still in effect and bound by its rules (not a black box).
Use case: drive trading directly from AI analysis while the system enforces risk control and constraints—capturing AI capability while keeping things auditable and controllable.
News & Event-Driven Trading
Features: news and sentiment parsing, event-driven signals, and responses to macro and unexpected events; the per-pair execution config is still set by the user, with risk control enforced uniformly by the system.
Use case: auto-generate signals or change direction based on news or events to react to macro policy shifts, black swans, and similar market impacts.
Exchanges and Data
Features: Multi-exchange connectivity, API and trading pair management, quotes and candlestick data, trading permissions and real-time sync.
Use case: Connect and manage accounts and quotes across exchanges in one place, providing data and execution for strategy, backtest, and live; complete exchange and API setup before going live.
Self-Hosted Deployment
Features: Finance-grade architecture, multi-strategy parallelism, local data storage, encryption and full audit; you own the server and system resources, config and keys stored encrypted.
Use case: Keep data and assets in your own environment for compliance and security; when changing sensitive config such as keys, delete and reconfigure.
For detailed operations and configuration of each module, see the corresponding docs in the sidebar; recommended reading order is on the home page under Recommended Reading Order.