Sign InOpen Brain
GitHubGitHub RepoNeeds Review

shy3130/tick-stock-panel

Tick Stock Panel is a self-hosted A-share research stack with screening, backtesting, monitoring, and an AI assistant whose 18 read-only tools expose auditable data calls.

GitHub · Trending today
Open Source Open MarkdownOpen JSON
Source Summary

Tick Stock Panel packages A-share screening, monitoring, and backtesting in a self-hosted Docker app. It includes **25 strategies**, computes **68 indicator and signal columns**, and gives its assistant **18 read-only tools** with inspectable call parameters, timing, and result summaries.

Practical Implication

Agent builders can study its fail-closed tool access, visible tool traces, local Parquet storage, and extension model: backend and frontend modules are discovered through isolated directories and can be removed without changing core files. Data-source capabilities are routed independently so providers can change without altering metric or backtest conventions.

Agent-Ready Context
Tick Stock Panel packages A-share screening, monitoring, and backtesting in a self-hosted Docker app. It includes **25 strategies**, computes **68 indicator and signal columns**, and gives its assistant **18 read-only tools** with inspectable call parameters, timing, and result summaries.

Agent builders can study its fail-closed tool access, visible tool traces, local Parquet storage, and extension model: backend and frontend modules are discovered through isolated directories and can be removed without changing core files. Data-source capabilities are routed independently so providers can change without altering metric or backtest conventions.

It is a personal open-source research project, not trading or recommendation software. Some data sources require separate API keys, the packaged image omits certain plugins, and Codex CLI mode mounts local credentials read-only and should be used only on a trusted machine.
Connected Context · Feed7 Judgment

This is a concrete domain-agent implementation of bounded, inspectable tooling: read-only assistant actions, visible traces, stable local data conventions, and removable modules constrain behavior without hiding extensibility. It supports structured domain interfaces over generic tool access, while its personal-project status and credential assumptions limit how far the pattern can be generalized to production or multi-user systems.

An Empirical Study of Harness Design for Coding AgentsThe app demonstrates an elaborate domain toolset, while the harness study cautions that such tooling must be justified per model and budget rather than assumed to outperform simpler interfaces.The Next Game Engine Won't Have a Manual — Arturo Nunez, NereuIts stable metric, backtest, and provider conventions exemplify the domain-native vocabulary that Nereu argues agents need instead of generated integration glue.MCP Apps: Give the Model Data, Give the User a UI — Dustin Mihalik, IndeedIts separate backend and frontend modules align with the recommendation to keep data exploration independent from rendering, preserving inspectable tool work before presentation.Your company brain will leak secrets: how we stopped it for big banks — Tanmai Gopal, PromptQLRead-only tools and read-only credential mounts reinforce bounded access, but the shared-memory guidance shows that production multi-user use would additionally require per-request identity and user-scoped authorization.
Context Map
toolsdatacoding#tool-use#dev-ux#context-engineering
Uncertainty
It is a personal open-source research project, not trading or recommendation software. Some data sources require separate API keys, the packaged image omits certain plugins, and Codex CLI mode mounts local credentials read-only and should be used only on a trusted machine.