📊 数据分析 — Top 10 AI Agent 工具

把 Excel / CSV / JSON 扔给 AI,让它自动画图、找规律、写结论。支持 pandas、Jupyter、BI 工具集成,适合数据产品、业务分析、运营报表等场景,让每个人都有数据分析师。

共收录 67 个工具 · 显示评分最高 10

1

K-Dense-AI/scientific-agent-skills

精选Python

A set of ready to use Agent Skills for research, science, engineering, analysis, finance and writing.

Stars
100
2

agent-infra/sandbox

精选Python

All-in-One Sandbox for AI Agents that combines Browser, Shell, File, MCP and VSCode Server in a single Docker container.

Stars
100
docker run --security-opt seccomp=unconfined --rm -it -p 8080:8080 ghcr.io/agent-infra/sandbox:latest
3

OpenSenseNova/SenseNova-Skills

精选Python

Modular SenseNova skills for building AI-powered office assistants and productivity workflows

Stars
100
4

rilldata/rill

精选Go

The fastest business intelligence tool for humans and agents.

Stars
100
5

arabold/docs-mcp-server

精选TypeScript

Grounded Docs MCP Server: Open-Source Alternative to Context7, Nia, and Ref.Tools

Stars
100
npx @arabold/docs-mcp-server@latest scrape react https://react.dev/reference/react
6

ghostwright/phantom

精选TypeScript

An AI co-worker with its own computer. Self-evolving, persistent memory, MCP server, secure credential collection, email identity. Built on the Claude Agent SDK.

Stars
100
7

Kaelio/ktx

精选TypeScript

ktx is an executable context layer for data and analytics agents 🐙 Allow Claude Code, Codex, and any AI agent to query data accurately through MCP with skills, memory and a semantic layer

Stars
100
8

wshobson/maverick-mcp

精选Python

MaverickMCP - Personal Stock Analysis MCP Server

Stars
100
brew install ta-lib
9

antvis/mcp-server-chart

精选TypeScript

🤖 A visualization mcp & skills contains 25+ visual charts using @antvis. Using for chart generation and data analysis.

Stars
100
10

scouter-project/scouter

精选Java

Scouter is an open source APM (Application Performance Management) tool.

Stars
100

💡 如何选择合适的 数据分析 工具?

评分是怎么算的?+

Trove 的评分包含 4 个维度:文档质量(Doc)、代码质量(Code)、社区活跃度(Community)和近期更新(Activity),总分 25 分,并划分为精选(≥20)、已验证(≥12.5)、社区(<12.5)三档。

如何选择适合自己的工具?+

先看 tier(精选/已验证优先),再看 stars 和近期更新时间,最后看 install_hint 确认安装方式是否符合你的环境(npm/pip/go 等)。

这些工具支持哪些 AI 平台?+

大多数工具以 MCP 协议为标准,兼容 Claude、OpenClaw、Codex、Cursor 等主流 AI 平台。部分工具还提供 OpenAI Function / LangChain Tool 格式。

如何把自己的工具上榜?+

在 GitHub 发布你的工具,带上相关 topic(如 mcp-server、ai-agent-skills),Trove 的爬虫会自动收录并评分。也可以到 opentrove.ai/publish 主动提交。

数据分析 - 最佳 AI Agent 工具 Top 10 | Trove