wzn1118 GitHub avatar

AsteriaAnalyst

wzn1118

A local workstation that streamlines enterprise data analysis, statistical testing, and management report creation with a traceable pipeline from data ingestion to versioned report delivery.

Stars

238

7-day growth

No data

Forks

4

Open issues

0

License

No data

Last updated

2026-07-28

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

Combines a comprehensive statistical method catalog (362 methods, 81 runnable) with a formal report generation pipeline that enforces deterministic computation and evidence verification, all in a local desktop application with collaborative revision workflows.

Who it is for

  • Data analysts and business intelligence professionals in enterprises
  • Statisticians and data scientists needing a reproducible analysis environment
  • Managers and report authors requiring structured report generation and revision tracking
  • Developers and contributors interested in extending analysis capabilities via Skill, Feature Trial, and custom agents

Use cases

  • Transform raw sales, customer, or inventory data into auditable management reports with derived metrics and charts.
  • Conduct statistical hypothesis testing (t-tests, ANOVA, chi-square) and regression analysis within a guided interface.
  • Perform data quality assessment including missing values, outliers, and field type validation.
  • Manage iterative report revisions with annotations, attachments, version tracking, and difference viewing.

Strengths

  • Provides a traceable data analysis pipeline with deterministic computation and evidence validation for formal reports.
  • Includes a large catalog of 362 statistical methods with 4,028 method cards for flexible field binding and result generation.
  • Supports local, offline execution from source code on Windows with no cloud dependency.
  • Offers extensibility layers (Skill, Feature Trial, Report Agent Team) for custom analysis workflows.

Considerations

  • Currently only supports Windows local environment; no macOS or Linux support.
  • Portable version is still under development; current use requires manual source code setup with Python 3.11 and Node.js 20+.
  • All documentation and interface language is primarily Chinese, which may limit adoption for non-Chinese-speaking users.

README quick start

快速开始

Description

Local-first data-to-decision delivery workbench.

Related repositories

Similar projects matched by category, topics, and programming language.

lopopolo
Featured
lopopolo GitHub avatar

harness-engineering

Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.

AI & Machine LearningAI Agents
2,390
slvDev
Featured
slvDev GitHub avatar

esp32-ai

A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.

AI & Machine LearningLarge Language Models
1,960
littledivy
Featured
littledivy GitHub avatar

mimic

mimic captures traffic from any iOS or web app and automatically generates a Python client library that lets you call the app's API like a regular library.

AI & Machine Learning
1,482