Open-source AI data analysis agents (2026)

AI data analysis agents with public source code you can read, self-host and extend. Here are the top 25 of 44 from the AgentScout directory.

Updated October 21, 2026

How we picked and ranked: tools are matched by category, the pricing each maker states and what each tool says it does. They are ranked by GitHub stars as recorded on each listing (link checks 2026-10-22); tools without a tracked repo follow, by listing maturity. No paid placements.

1. 

   1. Paperclip

   business agentsOpen source★ 103,425 GitHub stars

   Self-hosted app for running a team of AI agents like a small company, with org charts, goals, budgets and approval gates across Claude Code, Codex, OpenClaw and other harnesses.

   Pricing (as stated): Open source · Mature

2. 

   2. PPT Master

   productivityOpen source★ 63,293 GitHub stars

   AI tool that turns documents or topics into native, editable PowerPoint decks with real shapes, charts, transitions and narration from speaker notes.

   Pricing (as stated): Open source · Mature

3. 

   3. OpenViking

   memory & RAGOpen source★ 40,217 GitHub stars

   Context database for AI agents that keeps memory, knowledge and skills in one inspectable virtual filesystem agents can navigate.

   Pricing (as stated): Open source · Mature

4. 

   4. Tabby

   codingOpen source + cloud★ 33,913 GitHub stars

   Self-hosted AI coding assistant that offers an on-premises alternative to GitHub Copilot with no database or cloud service required.

   Pricing (as stated): Open source + cloud · Mature

5. 

   5. Chroma

   memory & RAGOpen source + cloud★ 29,512 GitHub stars

   Open-source search and vector database widely used for agent memory and RAG.

   Pricing (as stated): Open source + cloud · Mature

6. 

   6. Teable

   productivityOpen source + cloud★ 21,892 GitHub stars

   AI spreadsheet and database for business with built-in agents.

   Pricing (as stated): Open source + cloud · Mature

7. 

   7. WrenAI

   researchOpen source + cloud★ 17,881 GitHub stars

   Generative BI for agents: governed text-to-SQL with a semantic context layer.

   Pricing (as stated): Open source + cloud · Mature

8. 

   8. Memori

   memory & RAGOpen source + cloud★ 17,149 GitHub stars

   An LLM-, database- and framework-agnostic memory layer that turns what agents do and say into structured, persistent state they can recall in later runs. Open source to self-host, or use Memori Cloud with an API key.

   Pricing (as stated): Open source to self-host; Memori Cloud has a free tier. · Mature

9. 

   9. MCP Toolbox for Databases

   MCP serversOpen source★ 16,669 GitHub stars

   Open-source MCP server from Google for connecting agents to databases.

   Pricing (as stated): Open source · Mature

10. 

    10. SurfSense

    researchOpen source★ 16,459 GitHub stars

    Privacy-focused, open-source NotebookLM alternative with a research agent over your sources.

    Pricing (as stated): Open source · Mature

11. 

    11. InsForge

    app buildersOpen source + cloud★ 13,129 GitHub stars

    Open-source backend platform that gives coding agents a database, auth and storage.

    Pricing (as stated): Open source + cloud · Mature

12. 

    12. txtai

    memory & RAGOpen source★ 13,024 GitHub stars

    All-in-one Python framework for semantic search, LLM orchestration and agents built on an embeddings database of vector, graph and relational indexes.

    Pricing (as stated): Free and open source (Apache-2.0) · Mature

13. 

    13. LanceDB

    memory & RAGOpen source + cloud★ 11,684 GitHub stars

    Open-source multimodal vector database for search, RAG and agent memory.

    Pricing (as stated): Open source + cloud · Mature

14. 

    14. Activeloop

    memory & RAGOpen source + cloud★ 9,252 GitHub stars

    Deep Lake, a multimodal database for AI that stores vectors, images, text and video so agents and RAG apps can search and retrieve them.

    Pricing (as stated): Open source + cloud · Mature

15. 

    15. Baserow

    no-code buildersOpen source + cloud★ 6,184 GitHub stars

    No-code platform for databases, apps, automations and AI agents, an Airtable alternative available as cloud or self-hosted.

    Pricing (as stated): Free plan; Premium $10/user/mo yearly ($12 monthly), Advanced $18 ($22), Enterprise on request; self-host available (open core, MIT) · Mature

16. 

    16. LobsterAI

    personal agentsOpen source★ 6,119 GitHub stars

    NetEase Youdao's desktop agent for data analysis, slides, documents and web research.

    Pricing (as stated): Open source · Mature

17. 

    17. draw.io MCP

    productivityOpen source★ 5,669 GitHub stars

    The official draw.io MCP server, so Claude, ChatGPT, Cursor and other assistants can create and edit flowcharts, architecture diagrams and other draw.io diagrams right in the chat. Free and needs no sign-in.

    Pricing (as stated): Free; hosted MCP App server needs no sign-in. · Mature

18. 

    18. MCP-UI

    MCP serversOpen source★ 5,222 GitHub stars

    SDK that lets MCP servers send interactive web components such as forms, charts and buttons that chat hosts render inside the conversation.

    Pricing (as stated): Open source · Mature

19. 

    19. DeepAnalyze

    researchOpen source★ 4,727 GitHub stars

    Agentic LLM from Renmin University that autonomously runs data science pipelines and produces analyst-grade research reports.

    Pricing (as stated): Open source · Active

20. 

    20. AutoDev

    codingOpen source★ 4,558 GitHub stars

    Multi-agent development platform built on Kotlin Multiplatform for research, coding, review and data queries across IntelliJ, VS Code, CLI and more.

    Pricing (as stated): Open source · Active

21. 

    21. Jupyter AI

    codingOpen source★ 4,417 GitHub stars

    Official JupyterLab extension that connects AI agents and chat to notebooks.

    Pricing (as stated): Open source · Active

22. 

    22. AntV MCP Server Chart

    MCP serversOpen source★ 4,400 GitHub stars

    MCP server from AntV that lets agents generate more than 25 chart types.

    Pricing (as stated): Open source · Active

23. 

    23. CodeGraphContext

    codingOpen source★ 4,293 GitHub stars

    MCP server and CLI that index local code into a graph database so AI assistants can query code relationships.

    Pricing (as stated): Open source · Active

24. 

    24. Excel MCP Server

    MCP serversOpen source★ 4,244 GitHub stars

    MCP server that lets agents create and edit Excel files with formulas and charts.

    Pricing (as stated): Open source · Active

25. 

    25. OpenScience

    researchOpen source★ 4,043 GitHub stars

    Research agent workbench that reads the literature, writes and runs code and experiments and logs every step, with skills and connectors for databases like PubMed, UniProt and arXiv.

    Pricing (as stated): Open source · Active

FAQ

What are the best open-source AI data analysis agents?

Ranked by tracked GitHub stars, the top open-source AI data analysis agents in our directory are Paperclip, PPT Master, OpenViking, Tabby, Chroma. Stars measure popularity, not fit, so compare a few against your own task.

How many open-source AI data analysis agents does AgentScout list?

44 tools match. This page shows the top 25. Pricing mix on this page: Open source (16), Open source + cloud (9).

How much do these tools cost?

Pricing is what each maker states on their site. Open-source tools are free to self-host but may need a paid model API key or offer paid cloud plans; freemium tools have a free plan with limits. Check each official site.

Where can I see every tool for data analysis?

Our task page lists all 75 tools we match to data analysis.

Related: All tools for data analysis · MCP servers (16) · memory & RAG (9) · research (6) · coding (5)

By role: For sales teams · For researchers

All popular searches · AI agents by role · Free tools

Best-of lists: OpenViking alternatives · All best lists

Related categories: Memory & RAG · Coding · Research · MCP servers · Productivity

Facts come from our directory listings; pricing is as each maker states it and can change. Check official sites before you choose.