Fast AI Market Analysis
Structured, low-latency analysis with memory, ensemble voting, and confidence calibration. Compare views across OpenAI, Claude, Gemini, DeepSeek, Grok and more.
Templates are only the starting point. Create, AI-generate or freely edit Python strategies and chart indicators, then take the same strategy contract from reproducible backtests to live execution on infrastructure you control. Durable workers, auditable orders and recovery stay in one stack.
QUANTDINGER
/ CONTROL PLANE
01 Resolving market + instrument contract
02 Reading multi-timeframe structure
03 Generating Strategy API V2 source
04 Handing off deterministic backtest
def initialize(context): g.symbol = "Crypto:BTC/USDT@okx:swap"
context.set_universe([g.symbol]) context.subscribe(frequency="1m"
) context.set_warmup(200)def handle_data(context, data): bars = get_history(200, "1m"
, "close"
, g.symbol) signal = regime_model(bars) order_target_percent(g.symbol, signal)Research to execution in one product — AI analysis, charting, strategy code, backtests, quick trade, and live operations connected from day one.
Structured, low-latency analysis with memory, ensemble voting, and confidence calibration. Compare views across OpenAI, Claude, Gemini, DeepSeek, Grok and more.
Start from 16 built-in templates or write your own. Create, AI-generate and freely edit Python strategies, portfolio logic, trading bots and chart indicators. One Strategy API V2 contract carries executable strategies from reproducible backtests to live deployment. Creation is not limited to preset templates; concurrent live runs follow deployment resources and plan limits.
Run reproducible server-side backtests, then search declared parameters with random, grid or TPE optimization. Bar-count walk-forward validation, a blind holdout and robustness diagnostics help compare parameter stability.
Grid, Martingale, Trend Following and DCA out of the box. Signal-only mode maintains an internal virtual account with fills, positions, PnL and equity without sending broker orders; live execution remains explicitly separate.
One Docker Compose stack brings up separate API, trading, scheduler, Celery and migration roles. Your keys, strategies, AI history and trades remain on infrastructure you control.
PostgreSQL commands, renewable leases, heartbeats and fencing tokens protect durable execution. Optional Prometheus, Grafana and Alertmanager add production visibility.
Whether you trade solo, run a quant team, build a product, or operate a fund — QuantDinger is shaped for the way you actually work.
Solo traders and quant enthusiasts who want AI, charting, backtests and bots in one workspace — instead of juggling 5 tools.
Teams that want a unified toolchain — data ingestion, strategy code, backtests, live execution, and a shared history of experiments.
Developers who want a fast path from Python idea → backtest → live execution, with a documented SDK and clear extension points.
Research desks and operators that cannot send keys, alpha, or trading history to a hosted SaaS. Everything stays inside your infra.
Founders who need users, billing, credits, OAuth and payments in the stack from day one — not months of re-building plumbing.
Internal desks wanting one integrated platform for research, strategy code, execution, alerts, and operator-side admin controls.
The same deployable stack adapts to an internal research lab, a live strategy incubator, a customer-facing product, or a classroom.
Stand up a private quant research and backtesting platform for your team — reproducible runs, shared strategy library, saved snapshots.
Build consumer or pro-grade AI trading assistants on top of ensemble analysis, calibration, and memory — with a working UI out of the box.
Run a strategy incubator end-to-end: ideation, Python code, backtest, paper trade, then graduate to live with small size.
Offer member-based trading signals or strategy subscriptions with built-in memberships, credits, and USDT TRC20 payments.
Ship a hands-on learning environment for quant finance classes and bootcamps — real Python strategies, real charts, safe paper trading.
Run a private operations console for a fund or family office: portfolio monitors, alerts, multi-user roles, and audit-friendly history.
QuantDinger ships a first-class Agent Gateway and works with the published 58-tool quantdinger-mcp 0.6.2 package from PyPI.
The published quantdinger-mcp 0.6.2 package exposes 58 callable tools through local and network transports.
pip install "quantdinger-mcp==0.6.2"
# Or run directly: uvx quantdinger-mcp==0.6.2
Issue a token with only Read, Write, Backtest, Notification or Trade access. Market and instrument allowlists, expiry, rate limits, paper-only restrictions, idempotency and audit logs remain server-enforced.
Path A · Hosted — sign up at ai.quantdinger.com, paper-only by design, T-scope rejected at issuance. Try in 30 seconds. Path B · Self-host — clone, docker compose up, you own scopes, exchange keys, and the live-trading kill switch. Same MCP wiring; only QUANTDINGER_BASE_URL changes.
snapshot → progress → result on long backtests — no blind polling.
AGENT_LIVE_TRADING_ENABLED; hosted SaaS pins it shut.
Six crypto venues share one catalog-driven routing layer. Where authoritative product metadata is available, QuantDinger can route direct, tokenized, or perpetual US and Hong Kong equity products; IBKR and Alpaca remain native broker workflows.
Open the mobile web app in your browser, or install the native Android build. iOS TestFlight coming soon.
Same full-feature app, optimised for phones. No install — just open and use.
m.quantdinger.com
Native install, splash screen, safe-area & push-ready. Android 7+.
www.quantdinger.com/download/app.apk
On Android, you may need to allow "Install from unknown sources" for your browser before installing.
TestFlight build coming soon — in the meantime, use the mobile web app.
A straight line from market view to autonomous execution, with a reproducible backtest safety net in between.
Pull multi-timeframe data, run ensemble AI analysis, inspect indicator signals and comparables — all in one workspace.
Configure a ready-made bot with the visual wizard, or write full Python indicators / strategies using our documented SDK.
Deterministic runs with realistic commissions, slippage, and leverage. Freeze every experiment by code hash and config snapshot.
Promote a verified strategy through an explicit deployment flow. Monitor PnL, equity, positions, alerts, worker ownership and idempotent order retries.
The turnkey deployment runs on one host today. Per-process shared market feeds, Kafka closed-bar and shard events, and PostgreSQL inboxes, leases, checkpoints and fencing let each role scale independently. A 100,000-strategy deployment remains a capacity target until staged load and failover tests pass.
Orchestrate leading models for research, and optionally use JEV System One as an auditable PASS / REJECT gate for entry orders with LLM fallback.
Yes. The default deployment is your own Docker Compose stack with PostgreSQL, Kafka, separate cache and job Redis services, isolated backend process roles, credentials, and environment under your control. It runs on one host by default and preserves clear boundaries for later multi-host or multi-cluster scaling.
Broker credentials and MFA secrets are encrypted with a stable, operator-controlled CREDENTIAL_ENCRYPTION_KEY. They are decrypted only in memory for authorized operations and should never appear in logs.
Absolutely. The 16 built-in templates are optional starting points, not a boundary. Create, AI-generate and freely edit Python strategies, portfolio logic, trading bots and chart indicators. The same Strategy API V2 contract drives reproducible backtests and live deployments; concurrent live runs still follow deployment resources and plan limits.
Crypto spot and perpetual workflows cover Binance, OKX, Bitget, Bybit, Gate and HTX. Exchange-listed equity products are enabled only when the venue catalog exposes authoritative metadata: Gate supports direct US/HK stock routing; OKX, Bitget and Bybit support eligible tokenized equities and stock perpetuals; Binance supports eligible stock perpetuals. HTX equity products remain disabled. Product availability still depends on venue, region, account permissions and listing status. Native broker workflows include IBKR and Alpaca.
The backend is Apache 2.0. The prebuilt frontend is source-available under a separate license that allows personal and qualified non-commercial use for free; commercial deployment requires a license — apply here. See TRADEMARKS.md and LICENSE in the repo.
The app itself is fully localized across 10 languages — English, Simplified & Traditional Chinese, Japanese, Korean, Vietnamese, Thai, French, German, and Arabic.
Yes — v5.5.1 includes a 58-tool Agent Gateway and works with the published quantdinger-mcp 0.6.2 package from PyPI.
Hosted is best when you want to try QuantDinger from an AI agent in 30 seconds, don't have private exchange keys to plug in, and are fine with paper-only execution — the multi-tenant instance pins paper_only=true and rejects T-scope at issuance, so no agent on the hosted endpoint can ever route real-money orders. Self-host is the right call when you have your own exchange API keys, private strategies/data, run behind a VPN, or eventually want live execution. Both paths use identical MCP wiring — only QUANTDINGER_BASE_URL changes.
Activate the $699 lifetime membership and receive a permanent QuantDinger commercial license plus lifetime SaaS VIP access. Then submit your details to register the license.
Pay once and unlock two permanent benefits at the same time.
The backend remains Apache 2.0. Commercial use of the prebuilt frontend is covered by the registered commercial license.
Maker of QuantDinger
OpenByte Inc. is a technology company focused on open-source innovation and intelligent software. We build reliable, transparent, and self-hostable digital infrastructure, turning AI, data engineering, and automation into practical products for developers, teams, and businesses. We believe great software should remain open and extensible while giving users full control over their data, systems, and choices.
Please read before using the software or engaging with anyone claiming to represent the project.
Any account, group, website, or “team member” selling a QuantDinger coin, presale slot, private round, airdrop claim, staking product, or paid VIP group is a scam and has no affiliation with us. If someone asks you to send funds, sign a wallet approval, or share an API key to “verify your account” — it is not us. When in doubt, verify through the official channels below.
Trading crypto, stocks, forex, futures, and derivatives carries substantial risk and may not be suitable for every investor. You can lose all of your invested capital. Past performance — including any backtest or simulated result produced by the software — is not indicative of future results.
QuantDinger is a technology platform. Nothing on this website, inside the software, or in any AI-generated output constitutes investment, financial, legal, or tax advice. You alone are responsible for every trading decision and its outcome.
The software is provided “AS IS”, without warranty of any kind, express or implied. You are responsible for securing your own deployment, API keys, infrastructure, and regulatory compliance in your jurisdiction. See the project LICENSE and TRADEMARKS.md for the full terms.
QuantDinger is a product of OpenByte Inc. “QuantDinger” and the QuantDinger logo are trademarks of the project. Unauthorized use — including impersonation, fake support, fake airdrops, or pay-to-join “QuantDinger” groups — will be reported and pursued. If you encounter impersonation, please report it to support@quantdinger.com.
Some markets, exchanges, and products are restricted or unavailable in certain jurisdictions. You are responsible for ensuring that your use of QuantDinger and any connected venue complies with the laws and regulations applicable to you.
In a self-hosted deployment, your API keys, strategies, AI history, and trade records stay on infrastructure you control. We never ask for your keys, seed phrase, or private wallet signatures. Anyone asking for them is not us.
Try the hosted app, or deploy the complete v5 stack on infrastructure you control.