# antvis/AVA

🤖 AI-native Visual Analytics framework build for agents.

Repository: https://github.com/antvis/AVA
Canonical: https://ross.abutalabs.com/products/antvis-ava
Homepage: https://ava.antv.vision/
Language: TypeScript
License: MIT
License Family: permissive
Topics: visualization, data-visualization, charts, insight, augmented-analytics, narrative-charts, auto-insight, chart-recommendation, chart-aigc, insight-gpt
Last push: 2026-06-09T02:09:02+00:00

## Health v2 (maintenance only)
Score: 78/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 86, release rhythm 55, longevity 100
- inputs: {"age_days": 2435, "days_push": 86, "days_rel": 86, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1499, forks 154 (observed 2026-08-28T04:04:54.086908+00:00)

## What it is
AVA is an AI-native visual analytics framework from AntV that lets users load data (CSV, JSON, URL), query it in natural language, and get LLM-powered analysis with generated chart visualizations. It runs in both browser and Node.js, automatically switching between in-memory processing and SQLite based on data size.

## Use cases
- ask questions about my data in natural language
- automatically generate charts from a csv file
- recommend the best chart type for my dataset
- build an ai agent that analyzes spreadsheets
- turn raw data into visualizations with an llm
- auto-insight discovery for data analysis

## When to choose
- you want LLM-driven data analysis and chart generation in JavaScript/TypeScript
- you need natural-language querying over CSV/JSON data in browser or Node.js
- you want automated chart recommendation and narrative visualization

## When to avoid
- you need a pure rule-based charting library without LLM dependencies
- you require offline analysis with no API key or LLM access
- you need a full BI dashboard platform rather than a developer framework

## Facets
- artifact type: framework
- maturity: active
- function: data-visualization, charts, nlp, llm-inference, rag, data-science
- domain: data-visualization, artificial-intelligence, large-language-models, data-science, analytics
- platform: browser, cross-platform
- tags: ai-native, augmented-analytics, chart-recommendation, auto-insight, narrative-charts, natural-language-querying, antv, nodejs, typescript

## Member repositories
- antvis/AVA (main) score 78

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:54.086908+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 2026-08-30T04:33:02.191308+00:00, confidence not recorded.
  - readme: https://github.com/antvis/AVA (fetched 2026-08-28T04:04:54.086908+00:00, sha 911484b6b91d)
  - homepage: https://ava.antv.vision/ (fetched 2026-08-29T11:38:22.030096+00:00, sha df5605f68e2f)
  - site_page: https://ava.antv.vision/documentation (fetched 2026-08-29T11:38:22.045216+00:00, sha be153642dd38)
- Data as of 2026-08-30T08:39:29.467469+00:00.