Source: https://seerepo.com/compare/microsoft/graphrag/vs/run-llama/llama_index
Markdown source: https://seerepo.com/compare/microsoft/graphrag/vs/run-llama/llama_index.md
Description: graphrag and llama_index share 10 technologies: azure-storage-blob, pyarrow, azure-search-documents, lancedb, azure-identity, litellm, nltk, jinja2, markitdown, and Pydantic. Both are written in Python.

# graphrag vs llama_index

graphrag and llama_index share 10 technologies: azure-storage-blob, pyarrow, azure-search-documents, lancedb, azure-identity, litellm, nltk, jinja2, markitdown, and Pydantic. Both are written in Python.

- [microsoft/graphrag](https://seerepo.com/r/microsoft/graphrag): A modular graph-based Retrieval-Augmented Generation (RAG) system
- [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: azure-storage-blob, pyarrow, azure-search-documents, lancedb, azure-identity, litellm, nltk, jinja2, markitdown, Pydantic
- Only in graphrag: azure-cosmos, FastAPI, Streamlit, altair, graphrag, spaCy, textblob, azure-core
- Only in llama_index: starlette, aiomysql, aiosqlite, async-lru, asyncpg, ibm-db, pgvecto-rs, pgvector, psycopg, psycopg2-binary, pyzmq, Redis, weaviate-client, oracledb, DuckDB, pymilvus, SQLite, tablestore, chromadb, falkordb, MySQL, pinecone, clickhouse-connect, gcsfs, pyiceberg, pymochow, pymysql, pyobvector, s3fs, tcvectordb, typesense, ElevenLabs, anyio, graphql-core, tornado, AIOHTTP, Ray, soupsieve, tinycss2, ipywidgets, matplotlib-inline, prompt-toolkit, matplotlib, Rich, SQLAlchemy, argon2-cffi, Google, google-auth-httplib2, google-auth-oauthlib, cryptography, pyjwt, msal, einops, firecrawl-py, guardrails-ai, llama-index-core, mem0ai, OpenAI, opencv-python, PaddlePaddle, tavily-python, torch, transformers, ibm-watsonx-ai, cohere, LangChain, tiktoken, MCP, sentence-transformers, dashscope, fastembed, flagembedding, sentencepiece, ModelScope, Ollama, openvino, scikit-learn, tritonclient, vLLM, datasets, exa-py, flashrank, hnswlib, langfuse, mlx, mlx-lm, nomic, optimum, paddleocr, peft, presidio-analyzer, tokenizers, beautifulsoup4, bleach, markupsafe, mistune, nbformat, newspaper3k, xlrd, pillow, bs4, html2text, unstructured, defusedxml, lxml, pymupdf, filetype, docx2txt, markdownify, docling, lxml-html-clean, nbconvert, pdf2image, pdfplumber, pypdf, pypdf2, tinytag, youtube-transcript-api, jsonschema-specifications, marshmallow, referencing, rfc3339-validator, docling-core, annotated-types, jsonschema, pydantic-core, opentelemetry-api, opentelemetry-semantic-conventions, prometheus-client, psutil, python-json-logger, boto3, docker, Alibaba Cloud, OpenTelemetry

## Side by side

| | graphrag | llama_index |
|---|---|---|
| Size | 51,789 lines written, 449 code files | 473,236 lines written, 2,055 code files |
| Who writes it | 2.6% of its commits signed by AI. With GitHub Copilot | 0.2% of its commits signed by AI. With Claude Code, Cursor, and GitHub Copilot |
| Activity | Last push November 2, 2026, 499 commits, 36,582 stars | Last push November 5, 2026, 7,963 commits, 52,820 stars |
| Tests | 129 test files | 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, graphrag or llama_index?

llama_index, with 473,236 lines written; graphrag has 51,789.

The proof: [run-llama/llama_index's code at commit 444fdf0](https://github.com/run-llama/llama_index/tree/444fdf0684707de62ebb447d658dba137dd9cb99)

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

llama_index, with 52,820 stars; graphrag has 36,582.

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

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

llama_index, with 1,607 test files; graphrag has 129.

The proof: [run-llama/llama_index's code at commit 444fdf0](https://github.com/run-llama/llama_index/tree/444fdf0684707de62ebb447d658dba137dd9cb99)

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

llama_index: its last push was on November 5, 2026, and graphrag's on November 2, 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, graphrag or llama_index?

graphrag: an AI signed 2.6% of its commits, with GitHub Copilot; in llama_index, 0.2%.

## Sources

- microsoft/graphrag: Read on November 7, 2026, at commit 34b2b67 (https://github.com/microsoft/graphrag/tree/34b2b67ae4601ad0b47bcd179fbe3f2a23aa0857)
- 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.