tick-stock-panel
TSP自托管、零运维的 A 股「自建策略 + 监控 + 回测」量化工作台 | LLM能力驱使策略定制+个股分析+复盘 | 自由接入第三方数据源与个性化扩展数据 | 个人开源
What is tick-stock-panel?
TSP自托管、零运维的 A 股「自建策略 + 监控 + 回测」量化工作台 | LLM能力驱使策略定制+个股分析+复盘 | 自由接入第三方数据源与个性化扩展数据 | 个人开源
Overview of tick-stock-panel
What it is
TSP (Tick-Stock-Panel) is a self-hosted, zero-maintenance quantitative workstation for A-shares (Chinese stocks). It provides a unified platform for building custom strategies, monitoring the market, and running backtests. The project is open-source and designed for personal use, with all core capabilities exposed as interfaces. It is not intended as investment or charting software and does not include features like AI stock recommendations or limit-up predictions. Data sources are pluggable, allowing users to connect third-party data providers. The project is for learning and research purposes only.
Key features
- Capability Routing Matrix: Routes 6 types of datasets independently by source capability, allowing source changes without altering metrics or backtest results.
- Unified Enriched Data Pipeline: Stores 15 base columns and calculates 68 indicator/signal columns on the fly; strategy, backtest, monitoring, and review all consume the same data.
- Strategy Engine: Supports fully custom strategies, custom signals, and AI-generated strategies, with millisecond-level scanning of all A-shares.
- Backtest Research: Offers factor/strategy/minute-level backtesting with T+1, fees, slippage, and factor attribution.
- Factor Platform: Includes a DSL for custom factors, combination testing, and bidirectional linkage with strategies.
- Market Monitoring: Covers pre-market, intraday, and deviation anomalies with real-time pop-ups, voice broadcasts, and Feishu push notifications.
- Open API and MCP Server: Provides a Token-based API with 6 permission levels and 65 endpoints, plus an MCP server with 12 tools for AI client integration.
- AI Chat Assistant: Allows querying all platform data via natural language, with traceable tool usage.
Use cases
- Building and backtesting custom quantitative trading strategies for A-shares.
- Monitoring market anomalies and receiving real-time alerts during trading hours.
- Conducting factor research and mining multi-factor combinations.
- Extending the platform with custom data sources, pages, or backend modules.
- Using the open API or MCP server to integrate with external AI clients or custom tools.
Getting started
See the repository README for detailed installation and quick-start instructions.
License and pricing
The project is licensed under MIT. It is open-source and free to use.
Based on the project's public README and repository metadata.