Source: https://seerepo.com/compare/odysseus-dev/odysseus/vs/run-llama/llama_index
Markdown source: https://seerepo.com/compare/odysseus-dev/odysseus/vs/run-llama/llama_index.md
Description: odysseus and llama_index share 12 technologies: psycopg2-binary, SQLAlchemy, cryptography, MCP, pillow, beautifulsoup4, pypdf, pymupdf, pdfplumber, markitdown, youtube-transcript-api, and Pydantic. Both are written in Python.

# odysseus vs llama_index

odysseus and llama_index share 12 technologies: psycopg2-binary, SQLAlchemy, cryptography, MCP, pillow, beautifulsoup4, pypdf, pymupdf, pdfplumber, markitdown, youtube-transcript-api, and Pydantic. Both are written in Python.

- [odysseus-dev/odysseus](https://seerepo.com/r/odysseus-dev/odysseus): Self-hosted AI workspace. 
- [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: psycopg2-binary, SQLAlchemy, cryptography, MCP, pillow, beautifulsoup4, pypdf, pymupdf, pdfplumber, markitdown, youtube-transcript-api, Pydantic
- Only in odysseus: FastAPI, uvicorn, Postgres, bcrypt, pyotp, onnxruntime, faster-whisper, rapidocr, yt-dlp, markdown, qrcode, nh3, pypdfium2
- Only in llama_index: starlette, aiomysql, aiosqlite, async-lru, asyncpg, azure-search-documents, azure-storage-blob, ibm-db, pgvecto-rs, pgvector, psycopg, pyzmq, Redis, weaviate-client, pyarrow, lancedb, 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, argon2-cffi, azure-identity, Google, google-auth-httplib2, google-auth-oauthlib, 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, 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, bleach, markupsafe, mistune, nbformat, newspaper3k, xlrd, bs4, html2text, unstructured, defusedxml, jinja2, lxml, filetype, docx2txt, markdownify, docling, lxml-html-clean, nbconvert, pdf2image, pypdf2, tinytag, 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

| | odysseus | llama_index |
|---|---|---|
| Size | 765,982 lines written, 754 code files | 473,236 lines written, 2,055 code files |
| Who writes it | 11% of its commits signed by AI. With Claude Code, Codex, and Cursor | 0.2% of its commits signed by AI. With Claude Code, Cursor, and GitHub Copilot |
| Activity | Last push November 4, 2026, 2,596 commits, 95,062 stars | Last push November 5, 2026, 7,963 commits, 52,820 stars |
| Tests | 1,737 test files. 57.3% 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, odysseus or llama_index?

odysseus, with 765,982 lines written; llama_index has 473,236.

The proof: [odysseus-dev/odysseus's code at commit c21980f](https://github.com/odysseus-dev/odysseus/tree/c21980f5a6d1cb84db8c8ab0f488cefc7764eb3f)

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

odysseus, with 95,062 stars; llama_index has 52,820.

The proof: [odysseus-dev/odysseus on GitHub](https://github.com/odysseus-dev/odysseus)

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

odysseus, with 1,737 test files; llama_index has 1,607.

The proof: [odysseus-dev/odysseus's code at commit c21980f](https://github.com/odysseus-dev/odysseus/tree/c21980f5a6d1cb84db8c8ab0f488cefc7764eb3f)

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

llama_index: its last push was on November 5, 2026, and odysseus'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, odysseus or llama_index?

odysseus: an AI signed 11% of its commits, with Claude Code, Codex, and Cursor; in llama_index, 0.2%.

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

## Sources

- odysseus-dev/odysseus: Read on November 4, 2026, at commit c21980f (https://github.com/odysseus-dev/odysseus/tree/c21980f5a6d1cb84db8c8ab0f488cefc7764eb3f)
- 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.