# iDC-NEU/YiGraph

YiGraph is an LLM-driven agent for autonomous Graph Data Analytics based on Analytics-Augmented Generation.  易图（YiGraph）是一套基于 AAG（分析增强生成）框架构建的图分析智能体系统，致力于挖掘数据之间的关联关系，释放数据价值。

Repository: https://github.com/iDC-NEU/YiGraph
Canonical: https://ross.abutalabs.com/products/yigraph
Language: Python
License Family: other
Last push: 2026-07-24T08:22:44+00:00

## Health v2 (maintenance only)
Score: 61/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 94, release rhythm 35, longevity 30
- inputs: {"age_days": 425, "days_push": 40, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1227, forks 96 (observed 2026-08-28T04:04:03.295954+00:00)

## What it is
YiGraph is an LLM-driven agent system for autonomous graph data analytics built on the Analytics-Augmented Generation (AAG) framework. It extracts entities and relationships from raw data sources like logs, documents, and tables to build graph data, then answers natural-language business questions by planning and executing verifiable graph computations and generating interpretable analysis reports.

## Use cases
- analyze relationships in complex data with natural language questions
- extract entities and relations from documents and logs into a knowledge graph
- financial anti-money-laundering graph analysis
- generate interpretable analysis reports from graph data
- run graph algorithms via an LLM agent without writing queries
- turn business questions into executable graph analysis workflows

## When to choose
- you need natural-language-driven analysis over relational/graph data
- you want LLM answers grounded in verifiable graph computations rather than free-form chat
- you need automated entity and relationship extraction from heterogeneous raw data
- you need traceable, reviewable analysis reports for domains like finance or fraud detection

## When to avoid
- you need a simple chatbot without graph analytics
- your data has no meaningful relational structure
- you require a permissively licensed dependency - the repository lists no license
- you need a lightweight tool without LLM infrastructure

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, rag, nlp, machine-learning, data-science, analytics, chatbot
- domain: artificial-intelligence, large-language-models, data-science, analytics, graph-processing
- platform: python, cross-platform
- tags: graph-analytics, analytics-augmented-generation, llm-agent, knowledge-graph, graph-database, natural-language-analysis, anti-money-laundering, report-generation, ai-agents, natural-language-processing

## Member repositories
- iDC-NEU/YiGraph (main) score 61

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:03.295954+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:15:15.934307+00:00, confidence not recorded.
  - readme: https://github.com/iDC-NEU/YiGraph (fetched 2026-08-28T04:04:03.295954+00:00, sha 71ad1d8bcb2d)
- Data as of 2026-08-30T08:39:29.467469+00:00.