An open-source framework for AI agents to explore, analyze, and visualize data
A consistent data context lets your agent reason across different sources
Executed queries and their results give each answer a checkable basis
The question and the shape of the data guide the chart choice
You control where analysis runs and which model endpoint it uses
Explore local enginesAccuracy is measured against reference answers under published test conditions
Your agent provides the reasoning; AVA executes the data workflow
Get started with AVAMeasured on public benchmarks, built for answers you can verify
Your schema and data context give the analysis a factual starting point
Answers are built from executed queries and returned results
Follow the queries and results behind the answer, and check them yourself
Choose an Agent Skill, CLI, or TypeScript SDK
# install the skills for your agents
$ npx skills add antvis/AVA
# or add the marketplace in Claude Code
$ /plugin marketplace add antvis/AVA
# then, in a new agent session:
"Use the AVA skill to analyze /absolute/path/sales.csv,
compare sales by region, and generate a chart."Projects, extensions, and ideas from the AVA community
Revisit the SQL, results, and evidence behind your analysis in an editable notebook
Bring AVA v4 queries, streaming narratives, and AntV charts into DSH conversations
Run SQL on CSV data in a browser worker, then analyze and visualize with AVA
Trace analysis steps, timings, and SQL attempts through AVA’s public events
Explore data and generate charts directly from the AI agent you already use
A proposed chat bot for querying files and returning answers and charts in Feishu
A proposed Bitable plugin for analyzing and visualizing data inside Feishu
Connect, analyze, and visualize — with the tools your agent needs