PythonMITCreated Jun 18, 2026Last push 1d agoLatest release v0.3.37+449 stars this week+1.9K this month
Quick answers
What is tick-stock-panel?
Self-hosted quantitative trading workspace for Chinese stocks with AI assistance and comprehensive API capabilities.
What does tick-stock-panel do?
Tick Stock Panel (TSP) is a comprehensive, self-hosted quantitative research and trading platform tailored specifically for the Chinese A-share market. It provides a zero-maintenance environment for conducting deep market analysis, backtesting strategies, and monitoring live market data. The platform exposes all of its core capabilities via an Open API, allowing developers to integrate its engine into custom workflows. It features tools for factor mining, stock screening, and real-time monitoring. Additionally, it integrates an AI assistant and supports the Model Context Protocol (MCP) to automate complex quantitative analysis tasks.
Who is tick-stock-panel for?
TSP is designed for quantitative analysts, algorithmic traders, and developers focusing on the Chinese A-share market. It requires knowledge of financial modeling, backtesting methodologies, and server deployment.
How do I get started with tick-stock-panel?
npm install && npm start
How popular is tick-stock-panel on GitHub?
shy3130/tick-stock-panel has 8,105 stars and 1,993 forks on GitHub, and gained 449 stars in the last 7 days.
What license does tick-stock-panel use?
shy3130/tick-stock-panel is released under the MIT license.
Star history
since Sep 25, 2026
8.1K stars as of Nov 20, 2026. Measured daily since Sep 25, 2026; GitHub no longer exposes earlier star timestamps.
Update history
5 recorded
Nov 16, 2026New release v0.3.37 (previously v0.3.34).
Nov 8, 2026New release v0.3.34 (previously v0.3.23).
Oct 29, 2026New release v0.3.23 (previously v0.3.11).
Oct 21, 2026New release v0.3.11 (previously v0.3.5).
Oct 12, 2026Description changed from "TSP自托管、零运维的 A 股「选股 + 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" to "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".
Contribution activity
commits per day, last 52 weeks
1,102 commits in the last yearLessMore
Signals and awards
derived from tracked data
Rising fast
+449 stars this week
Very active
1,102 commits in 52 weeks
Permissive license
MIT
Continuous integration
Automated checks passing
What tick-stock-panel does
Tick Stock Panel (TSP) is a comprehensive, self-hosted quantitative research and trading platform tailored specifically for the Chinese A-share market. It provides a zero-maintenance environment for conducting deep market analysis, backtesting strategies, and monitoring live market data. The platform exposes all of its core capabilities via an Open API, allowing developers to integrate its engine into custom workflows. It features tools for factor mining, stock screening, and real-time monitoring. Additionally, it integrates an AI assistant and supports the Model Context Protocol (MCP) to automate complex quantitative analysis tasks.
TSP is designed for quantitative analysts, algorithmic traders, and developers focusing on the Chinese A-share market. It requires knowledge of financial modeling, backtesting methodologies, and server deployment.
Self-hosted architecture: Runs entirely on user-controlled infrastructure, ensuring data privacy and zero external maintenance.
Quantitative backtesting: Provides an engine to simulate and evaluate trading strategies against historical A-share data.
Factor mining tools: Includes utilities to discover, calculate, and analyze predictive alpha factors in the stock market.
Open API integration: Exposes all platform features through comprehensive APIs for custom algorithmic trading bots.
AI assistant integration: Connects with LLMs via MCP to provide intelligent insights and automate quantitative research.
Where teams use it
Develop trading strategies
Use the backtesting engine to evaluate the historical performance of custom multi-factor stock selection models.
Monitor A-share markets
Set up customized, real-time dashboards to track specific stock behaviors and market-wide quantitative metrics.
Automate factor calculation
Leverage the Open API to programmatically calculate and store complex technical and fundamental factors daily.
Analyze stocks with AI
Use the built-in AI assistant to interpret complex technical indicators and summarize stock performance.
参数按 K 段折外稳健分(0.6×中位+0.4×最差)排名而非样本内得分:主目标白名单 + 最小交易数门槛 + Top-20 全窗退化率 + 冠军收敛/高原判据;滚动样本外检验每折重优化防过拟合,冠军/最新折参数一键应用到策略
🛡️ 策略守护
发布的策略自动落基线,每日用新数据 K 段真实回测复验:退化自动判定 健康/观察/退役(交易数枯竭即退役),连续观察告警;退役只标记不删档,支持任意策略手动入护(尾随参考基线)。冠军按稳健分(中位+最差折)选出并做权重精调;健康冠军间低相关(日收益 Pearson≤0.7)可一键生成组合策略并入护;实验室战报聚合守护/挖掘/名额,挖掘名额满时新候选等位
🏛️ 网关居中的开放单体
面板密码会话与 Token 网关双通道并行;65 端点契约快照 + CI 守护,SSE 事件流与 MCP 平等开放
分发与二次开发须知:依据 MIT 协议,分发本软件或其任何部分(包括 fork 后发布、修改再发布、封装为自有产品或服务)时,必须完整保留原始版权声明与许可文本。未经版权所有者书面许可,移除、遮蔽或篡改版权署名、许可声明,或在再分发时隐匿本项目来源,均构成协议违约与著作权侵权,版权所有者保留依法追究责任的权利。
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.