Source: https://seerepo.com/compare/apache/superset/vs/run-llama/llama_index
Markdown source: https://seerepo.com/compare/apache/superset/vs/run-llama/llama_index.md
Description: superset and llama_index share 46 technologies: oracledb, psycopg2-binary, pyarrow, Redis, MySQL, clickhouse-connect, pymysql, Google, AIOHTTP, starlette, anyio, pyzmq, matplotlib, prompt-toolkit, Rich, SQLAlchemy, google-auth-oauthlib, pyjwt, cryptography, tiktoken, MCP, defusedxml, xlrd, jinja2, markupsafe, pillow, annotated-types, jsonschema-specifications, referencing, rfc3339-validator, jsonschema, Pydantic, pydantic-core, docker, OpenTelemetry, boto3, psutil, soupsieve, tinycss2, ipywidgets, matplotlib-inline, argon2-cffi, beautifulsoup4, bleach, prometheus-client, and python-json-logger. Both are written in Python.

# superset vs llama_index

superset and llama_index share 46 technologies: oracledb, psycopg2-binary, pyarrow, Redis, MySQL, clickhouse-connect, pymysql, Google, AIOHTTP, starlette, anyio, pyzmq, matplotlib, prompt-toolkit, Rich, SQLAlchemy, google-auth-oauthlib, pyjwt, cryptography, tiktoken, MCP, defusedxml, xlrd, jinja2, markupsafe, pillow, annotated-types, jsonschema-specifications, referencing, rfc3339-validator, jsonschema, Pydantic, pydantic-core, docker, OpenTelemetry, boto3, psutil, soupsieve, tinycss2, ipywidgets, matplotlib-inline, argon2-cffi, beautifulsoup4, bleach, prometheus-client, and python-json-logger. Both are written in Python.

- [apache/superset](https://seerepo.com/r/apache/superset): Apache Superset is a Data Visualization and Data Exploration Platform
- [run-llama/llama_index](https://seerepo.com/r/run-llama/llama_index): LlamaIndex is the document processing platform for AI

## What they share and what sets them apart

- In common: oracledb, psycopg2-binary, pyarrow, Redis, MySQL, clickhouse-connect, pymysql, Google, AIOHTTP, starlette, anyio, pyzmq, matplotlib, prompt-toolkit, Rich, SQLAlchemy, google-auth-oauthlib, pyjwt, cryptography, tiktoken, MCP, defusedxml, xlrd, jinja2, markupsafe, pillow, annotated-types, jsonschema-specifications, referencing, rfc3339-validator, jsonschema, Pydantic, pydantic-core, docker, OpenTelemetry, boto3, psutil, soupsieve, tinycss2, ipywidgets, matplotlib-inline, argon2-cffi, beautifulsoup4, bleach, prometheus-client, python-json-logger
- Only in superset: Flask, google-cloud-core, pymssql, Celery, Postgres, kombu, MongoDB, pandas-gbq, uvicorn, werkzeug, fastmcp, flask-cors, React, Express, cycler, fonttools, contourpy, alembic, flask-migrate, bcrypt, itsdangerous, joserfc, oauthlib, flask-login, authlib, mako, markdown-it-py, mdurl, pyxlsb, openpyxl, nh3, markdown, xlsxwriter, beartype, email-validator, msgspec, Gunicorn, botocore, jwt-decode, emotion, fontsource, antd, Ant Design, @emotion/react, classnames, react-resize-detector, ag-grid-community, react-ace, ace-builds, d3-scale, re-resizable, react-draggable, ag-grid-react, react-error-boundary, react-syntax-highlighter, react-window, @braintree/sanitize-url, dompurify, handlebars, markdown-to-jsx, react-markdown, rehype-raw, rehype-sanitize, remark-gfm, xss, D3, echarts, Zod, prop-types, MapLibre, supercluster, deck.gl, jsonwebtoken, hot-shots, winston, morgan
- Only in llama_index: aiomysql, aiosqlite, async-lru, asyncpg, azure-search-documents, azure-storage-blob, ibm-db, pgvecto-rs, pgvector, psycopg, weaviate-client, lancedb, DuckDB, pymilvus, SQLite, tablestore, chromadb, falkordb, pinecone, gcsfs, pyiceberg, pymochow, pyobvector, s3fs, tcvectordb, typesense, ElevenLabs, graphql-core, tornado, Ray, azure-identity, google-auth-httplib2, msal, einops, firecrawl-py, guardrails-ai, llama-index-core, mem0ai, OpenAI, opencv-python, PaddlePaddle, tavily-python, torch, transformers, ibm-watsonx-ai, cohere, LangChain, sentence-transformers, dashscope, fastembed, flagembedding, nltk, sentencepiece, litellm, ModelScope, Ollama, openvino, scikit-learn, tritonclient, vLLM, datasets, exa-py, flashrank, hnswlib, langfuse, mlx, mlx-lm, nomic, optimum, paddleocr, peft, presidio-analyzer, tokenizers, mistune, nbformat, newspaper3k, bs4, html2text, unstructured, lxml, pymupdf, filetype, docx2txt, markdownify, docling, lxml-html-clean, markitdown, nbconvert, pdf2image, pdfplumber, pypdf, pypdf2, tinytag, youtube-transcript-api, marshmallow, docling-core, opentelemetry-api, opentelemetry-semantic-conventions, Alibaba Cloud

## Side by side

| | superset | llama_index |
|---|---|---|
| Size | 1,918,985 lines written, 3,663 code files | 473,236 lines written, 2,055 code files |
| Who writes it | 9.2% of its commits signed by AI. With Claude Code, GitHub Copilot, Cursor, Devin, and Codex | 0.2% of its commits signed by AI. With Claude Code, Cursor, and GitHub Copilot |
| Activity | Last push November 4, 2026, 24,012 commits, 75,409 stars | Last push November 5, 2026, 7,963 commits, 52,820 stars |
| Tests | 3,041 test files. 61.8% of its code files have a test that imports them | 1,607 test files. 46.5% of its code files have a test that imports them |

- Size: Lines written by people and agents, without generated ones; code files, without tests.
- Who writes it: A commit counts as AI's when it carries its signature: a Co-Authored-By line, its author name or the merge of its branch.
- Activity: From GitHub and its history, on the day SeeRepo read it.
- Tests: The files that test the code, and the share of code files a test imports.

## Frequently asked questions

### Which is bigger, superset or llama_index?

superset, with 1,918,985 lines written; llama_index has 473,236.

The proof: [apache/superset's code at commit fcc13d4](https://github.com/apache/superset/tree/fcc13d4a301e81e5f5f2d82ba021e078b87187e7)

### Which has more GitHub stars, superset or llama_index?

superset, with 75,409 stars; llama_index has 52,820.

The proof: [apache/superset on GitHub](https://github.com/apache/superset)

### Which has more tests, superset or llama_index?

superset, with 3,041 test files; llama_index has 1,607.

The proof: [apache/superset's code at commit fcc13d4](https://github.com/apache/superset/tree/fcc13d4a301e81e5f5f2d82ba021e078b87187e7)

### Which was updated more recently, superset or llama_index?

llama_index: its last push was on November 5, 2026, and superset's on November 4, 2026.

The proof: [run-llama/llama_index's commits on GitHub](https://github.com/run-llama/llama_index/commits)

### Which has more commits signed by AI, superset or llama_index?

superset: an AI signed 9.2% of its commits, with Claude Code, GitHub Copilot, Cursor, Devin, and Codex; in llama_index, 0.2%.

The proof: [the commits each tool signed in apache/superset](https://seerepo.com/r/apache/superset/ai)

## Sources

- apache/superset: Read on November 4, 2026, at commit fcc13d4 (https://github.com/apache/superset/tree/fcc13d4a301e81e5f5f2d82ba021e078b87187e7)
- run-llama/llama_index: Read on November 5, 2026, at commit 444fdf0 (https://github.com/run-llama/llama_index/tree/444fdf0684707de62ebb447d658dba137dd9cb99)

## What is your repo built with?

Any public repo, with no account: https://seerepo.com/r/owner/repo/built, with the owner and name it has on GitHub.