Source: https://seerepo.com/compare/MemTensor/MemOS/vs/run-llama/llama_index
Markdown source: https://seerepo.com/compare/MemTensor/MemOS/vs/run-llama/llama_index.md
Description: MemOS and llama_index share 41 technologies: psycopg2-binary, pymysql, Redis, SQLite, Neo4j, pymilvus, OpenAI, Alibaba Cloud, anyio, starlette, MCP, soupsieve, Rich, SQLAlchemy, cryptography, pyjwt, nltk, tavily-python, tokenizers, scikit-learn, torch, transformers, LangChain, Ollama, chonkie, sentence-transformers, beautifulsoup4, defusedxml, jinja2, lxml, markdownify, markupsafe, xlrd, markitdown, pillow, annotated-types, jsonschema, jsonschema-specifications, referencing, Pydantic, and prometheus-client. MemOS is written in TypeScript and llama_index in Python.

# MemOS vs llama_index

MemOS and llama_index share 41 technologies: psycopg2-binary, pymysql, Redis, SQLite, Neo4j, pymilvus, OpenAI, Alibaba Cloud, anyio, starlette, MCP, soupsieve, Rich, SQLAlchemy, cryptography, pyjwt, nltk, tavily-python, tokenizers, scikit-learn, torch, transformers, LangChain, Ollama, chonkie, sentence-transformers, beautifulsoup4, defusedxml, jinja2, lxml, markdownify, markupsafe, xlrd, markitdown, pillow, annotated-types, jsonschema, jsonschema-specifications, referencing, Pydantic, and prometheus-client. MemOS is written in TypeScript and llama_index in Python.

- [MemTensor/MemOS](https://seerepo.com/r/MemTensor/MemOS): Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.
- [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, pymysql, Redis, SQLite, Neo4j, pymilvus, OpenAI, Alibaba Cloud, anyio, starlette, MCP, soupsieve, Rich, SQLAlchemy, cryptography, pyjwt, nltk, tavily-python, tokenizers, scikit-learn, torch, transformers, LangChain, Ollama, chonkie, sentence-transformers, beautifulsoup4, defusedxml, jinja2, lxml, markdownify, markupsafe, xlrd, markitdown, pillow, annotated-types, jsonschema, jsonschema-specifications, referencing, Pydantic, prometheus-client
- Only in MemOS: FastAPI, uvicorn, diskcache, py-key-value-aio, Postgres, pika, Qdrant, fastmcp, Preact, @deepseek-ai/dsh-session, @deepseek-ai/cordis, Vite, React, react-router-dom, electron-store, Electron, Express, Hono, rich-toolkit, authlib, itsdangerous, keyring, langsmith, NVIDIA, nvidia-cudnn-cu12, onnxruntime, safetensors, triton, Hugging Face, rank-bm25, docutils, et-xmlfile, magika, mammoth, markdown-it-py, mdurl, openpyxl, pdfminer-six, python-pptx, rich-rst, xlsxwriter, beartype, email-validator, jsonschema-path, openapi-pydantic, pathvalidate, coloredlogs, concurrent-log-handler, fastapi-cloud-cli, volcengine-python-sdk, @sinclair/typebox, deepseek-ai, yaml, @deepseek-ai/schemastery, Tailwind CSS, class-variance-authority, Radix UI, Framer, Lucide, @aws-sdk/credential-providers, @aws-sdk/client-bedrock, react-markdown, Zod, @hono/node-server
- Only in llama_index: aiomysql, aiosqlite, async-lru, asyncpg, azure-cosmos, azure-data-tables, azure-search-documents, azure-storage-blob, ibm-db, nebula3-python, oss2, pgml, pgvecto-rs, pgvector, pickleshare, psycopg, pyathena, pydrive, pylance, pymongo, python-arango, pyvespa, pyzmq, snowflake-sqlalchemy, tantivy, weaviate-client, aioboto3, pyarrow, lancedb, oracledb, DuckDB, pysolr, tablestore, aperturedb, astrapy, chromadb, dashvector, falkordb, jaguardb-http-client, MySQL, pinecone, clickhouse-connect, couchdb3, gcsfs, opendal, pyairtable, pyiceberg, pymochow, pyobvector, s3fs, tcvectordb, typesense, ElevenLabs, graphql-core, jupyter-core, jupyterlab-server, tornado, AIOHTTP, Ray, jupyterlab-pygments, tinycss2, ipywidgets, jupyter-server-terminals, jupyterlab-widgets, matplotlib-inline, prompt-toolkit, widgetsnbextension, matplotlib, argon2-cffi, argon2-cffi-bindings, azure-identity, Google, google-auth-httplib2, google-auth-oauthlib, msal, argilla, azure-ai-agents, azure-ai-inference, azure-ai-projects, contextual-client, diff-cover, einops, firecrawl-py, friendli-client, guardrails-ai, llama-cpp-python, llama-index-core, llama-index-embeddings-dashscope, llama-index-embeddings-huggingface, llama-index-embeddings-openai, llama-index-llms-anthropic, llama-index-llms-azure-openai, llama-index-llms-huggingface, llama-index-llms-llama-cpp, llama-index-llms-openai, llama-index-llms-openai-like, llama-index-node-parser-dashscope, llama-index-program-guidance, llama-index-readers-dashscope, llama-index-readers-database, llama-index-readers-remote, llama-index-readers-upstage, llama-index-readers-web, llama-index-response-synthesizers-google, llama-index-utils-azure, llama-index-utils-huggingface, llama-index-utils-qianfan, llama-index-vector-stores-google, llama-index-workflows, mem0ai, ms-swift, open-clip-torch, opencv-python, openinference-instrumentation-llama-index, openvino-tokenizers, PaddlePaddle, portkey-ai, reka-api, llama-index-instrumentation, ibm-watsonx-ai, cohere, tiktoken, dashscope, fastembed, flagembedding, llama-cloud, optimum-intel, sentencepiece, ai21, aleph-alpha-client, gigachat, guidance, igptai, konko, litellm, mixedbread, ModelScope, octoai, openvino, openvino-genai, premai, tritonclient, vLLM, voyageai, zep-python, zhipuai, agent-search, aimon, argilla-llama-index, assemblyai, bm25s, browserbase, cleanlab-tlm, cognee, colpali-engine, datasets, exa-py, flashrank, hnswlib, honeyhive, instructorembedding, isaacus, langfuse, llmlingua, llmsherpa, marvin, mlx, mlx-lm, nomic, notdiamond, optimum, optimum-habana, paddleocr, peft, presidio-analyzer, presidio-anonymizer, promptlayer, psychicapi, pydi-client, rank-llm, span-marker, superlinked, uptrain, vectorize-client, videodb, bleach, camelot-py, ghostscript, llama-index-readers-file, llama-index-readers-youtube-transcript, maincontentextractor, marker-pdf, mistune, nbformat, newspaper3k, nougat-ocr, pandocfilters, webencodings, bs4, html2text, unstructured, pymupdf, filetype, bagel, docx2txt, olefile, pytesseract, dgml-utils, docling, layoutir, llama-parse, lxml-html-clean, nbconvert, pdf2image, pdfplumber, pypdf, pypdf2, striprtf, svglib, tika, tinytag, youtube-transcript-api, fastjsonschema, fqdn, marshmallow, rfc3339-validator, rfc3986-validator, docling-core, pydantic-core, opentelemetry-api, opentelemetry-semantic-conventions, psutil, python-json-logger, boto3, docker, oci, OpenTelemetry

## Side by side

| | MemOS | llama_index |
|---|---|---|
| Size | 447,484 lines written, 898 code files | 473,236 lines written, 2,055 code files |
| Who writes it | 10.8% of its commits signed by AI. With Cursor, Claude Code, and GitHub Copilot | 0.2% of its commits signed by AI. With Claude Code, Cursor, and GitHub Copilot |
| Activity | Last push November 11, 2026, 1,631 commits, 12,352 stars | Last push November 8, 2026, 7,964 commits, 52,863 stars |
| Tests | 480 test files. 46.1% 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, MemOS or llama_index?

llama_index, with 473,236 lines written; MemOS has 447,484.

The proof: [run-llama/llama_index's code at commit fe107aa](https://github.com/run-llama/llama_index/tree/fe107aab65e46d1d07c80663182691970417bbd9)

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

llama_index, with 52,863 stars; MemOS has 12,352.

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

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

llama_index, with 1,607 test files; MemOS has 480.

The proof: [run-llama/llama_index's code at commit fe107aa](https://github.com/run-llama/llama_index/tree/fe107aab65e46d1d07c80663182691970417bbd9)

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

MemOS: its last push was on November 11, 2026, and llama_index's on November 8, 2026.

The proof: [MemTensor/MemOS's commits on GitHub](https://github.com/MemTensor/MemOS/commits)

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

MemOS: an AI signed 10.8% of its commits, with Cursor, Claude Code, and GitHub Copilot; in llama_index, 0.2%.

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

## Sources

- MemTensor/MemOS: Read on November 11, 2026, at commit 3a16e5f (https://github.com/MemTensor/MemOS/tree/3a16e5fe3048a209f722806f4123fa2e533588fd)
- run-llama/llama_index: Read on November 10, 2026, at commit fe107aa (https://github.com/run-llama/llama_index/tree/fe107aab65e46d1d07c80663182691970417bbd9)

## 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.