
QuantDinger
Self-hosted AI trading stack: research, strategy code, backtests, paper and live trading
- Pricing
- Open source
- Platforms
- Web, self-hosted, API
- GitHub stars
- 13.8K
- Last commit
- 1 day ago
- Language
- Python
- License
- Apache-2.0
About QuantDinger
QuantDinger is an open-source agent for finance and payments. It is available on Web, self-hosted and API.
Strategy code, broker credentials and market data stay under the operator's control in this local-first system. AI research feeds Python indicator and strategy development, followed by server-side backtesting, paper trading, live execution on crypto exchanges and brokers, and monitoring. Access is through a web UI, mobile H5, a human API, an Agent Gateway and MCP.
Factor Lab benchmarks up to 40 factors with out-of-sample checks and false-discovery control, while strategy evolution tunes parameters with walk-forward validation and a final holdout. The README warns that live trading can submit real orders, urges starting with paper trading and restricted API keys, and says it gives no investment advice. State lives in PostgreSQL.
What it does
- Strategy code and backtests
- Python strategies tested server-side.
- Factor Lab
- Benchmarks up to 40 factors with false-discovery control.
- Strategy evolution
- Random, grid or TPE parameter search with walk-forward validation.
- Paper and live execution
- Crypto exchanges and traditional brokers.
- Agent Gateway and MCP
- Workflows reachable by AI agents.
- Self-hosted
- PostgreSQL state, workers and audit logs.
Good for
- Backtest a trading idea in Python
- Rank factors before building a strategy
- Paper trade before going live
- Expose trading research to an AI client
Pricing
Open source
Apache-2.0; self-hosted
Prices change. Check ai.quantdinger.com before you buy.
QuantDinger FAQ
Can it place real orders?
Yes, when live trading is explicitly enabled; the README advises paper trading first.
Is it investment advice?
No, the project says it does not provide it.
What licence applies?
Apache-2.0.
Is QuantDinger free?
Yes. QuantDinger is open source, so you can use and self-host it for free.
What are the best alternatives to QuantDinger?
The closest alternatives to QuantDinger are daily_stock_analysis, Vibe-Trading, BettaFish, Bindu and DeepAnalyze.
Alternatives to QuantDinger

daily_stock_analysis
AgentLLM-driven stock analysis producing daily reports for A-share, HK and US markets
- Open source
- Open-source agent
- 72.9K GitHub stars
- Finance and payments

Vibe-Trading
AgentOpen-source finance research agent for backtests, swarm analysis and trade journals
- Open source
- Open-source agent
- 38.4K GitHub stars
- Finance and payments

BettaFish
AgentMulti-agent public opinion analysis system that mines social media and writes reports
- Open source
- Open-source agent
- 42.7K GitHub stars
- Analytics and data

Bindu
AgentFramework giving agents identity, A2A communication and payments
- Open source
- A2A agent
- 10K GitHub stars
- Multi-agent frameworks

DeepAnalyze
AgentOpen 8B agentic model that runs a full data science pipeline from raw data
- Open source
- Open-source agent
- 4.8K GitHub stars
- Analytics and data

BambooAI
AgentAI-powered data analysis workbench built for transparency, reproducibility and user…
- Open source
- Open-source agent
- 847 GitHub stars
- Analytics and data