Source: https://seerepo.com/compare/cvat-ai/cvat/vs/run-llama/llama_index
Markdown source: https://seerepo.com/compare/cvat-ai/cvat/vs/run-llama/llama_index.md
Description: cvat and llama_index share 20 technologies: psycopg2-binary, pyarrow, Redis, clickhouse-connect, azure-storage-blob, anyio, tornado, matplotlib, cryptography, pyjwt, Google, nltk, scikit-learn, lxml, pillow, defusedxml, pdf2image, jsonschema, psutil, and boto3. cvat is written in TypeScript and llama_index in Python.

# cvat vs llama_index

cvat and llama_index share 20 technologies: psycopg2-binary, pyarrow, Redis, clickhouse-connect, azure-storage-blob, anyio, tornado, matplotlib, cryptography, pyjwt, Google, nltk, scikit-learn, lxml, pillow, defusedxml, pdf2image, jsonschema, psutil, and boto3. cvat is written in TypeScript and llama_index in Python.

- [cvat-ai/cvat](https://seerepo.com/r/cvat-ai/cvat): CVAT is a leading data annotation platform for image, video, audio, and 3D datasets. It offers open-source, cloud, and enterprise products, as well as labeling services, with AI-assisted labeling, quality assurance, team collaboration, analytics, and developer APIs.
- [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, pyarrow, Redis, clickhouse-connect, azure-storage-blob, anyio, tornado, matplotlib, cryptography, pyjwt, Google, nltk, scikit-learn, lxml, pillow, defusedxml, pdf2image, jsonschema, psutil, boto3
- Only in cvat: Django, google-cloud-core, h5py, s3transfer, rq, django-rq, Postgres, Google Cloud Storage, asgiref, uvicorn, djangorestframework, lru-cache, React, React Router, react-router-dom, cycler, fonttools, contourpy, oauthlib, python3-saml, requests-oauthlib, django-allauth, pycocotools, imagesize, ruamel-yaml-clib, av, ruamel-yaml, kubernetes, azure-core, botocore, fabric, three, dompurify, classnames, antd, wavesurfer.js, @dnd-kit/core, @uiw/react-md-editor, react-color, react-intersection-observer, TanStack, @ant-design/compatible, Chart.js, react-grid-layout, Ant Design, onnxruntime-web, rehype-sanitize, react-markdown, prop-types
- Only in llama_index: starlette, aiomysql, aiosqlite, async-lru, asyncpg, azure-search-documents, ibm-db, pgvecto-rs, pgvector, psycopg, pyzmq, weaviate-client, lancedb, oracledb, DuckDB, pymilvus, SQLite, tablestore, chromadb, falkordb, MySQL, pinecone, gcsfs, pyiceberg, pymochow, pymysql, pyobvector, s3fs, tcvectordb, typesense, ElevenLabs, graphql-core, AIOHTTP, Ray, soupsieve, tinycss2, ipywidgets, matplotlib-inline, prompt-toolkit, Rich, SQLAlchemy, argon2-cffi, azure-identity, google-auth-httplib2, google-auth-oauthlib, 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, litellm, ModelScope, Ollama, openvino, 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, bs4, html2text, unstructured, jinja2, pymupdf, filetype, docx2txt, markdownify, docling, lxml-html-clean, markitdown, nbconvert, pdfplumber, pypdf, pypdf2, tinytag, youtube-transcript-api, jsonschema-specifications, marshmallow, referencing, rfc3339-validator, Pydantic, docling-core, annotated-types, pydantic-core, opentelemetry-api, opentelemetry-semantic-conventions, prometheus-client, python-json-logger, docker, Alibaba Cloud, OpenTelemetry

## Side by side

| | cvat | llama_index |
|---|---|---|
| Size | 341,391 lines written, 1,089 code files | 473,236 lines written, 2,055 code files |
| Who writes it | 0.1% of its commits signed by AI. With CodeRabbit, Codex, Claude Code, and GitHub Copilot | 0.2% of its commits signed by AI. With Claude Code, Cursor, and GitHub Copilot |
| Activity | Last push November 6, 2026, 6,058 commits, 17,088 stars | Last push November 5, 2026, 7,963 commits, 52,820 stars |
| Tests | 453 test files. 7% 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, cvat or llama_index?

llama_index, with 473,236 lines written; cvat has 341,391.

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, cvat or llama_index?

llama_index, with 52,820 stars; cvat has 17,088.

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

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

llama_index, with 1,607 test files; cvat has 453.

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, cvat or llama_index?

cvat: its last push was on November 6, 2026, and llama_index's on November 5, 2026.

The proof: [cvat-ai/cvat's commits on GitHub](https://github.com/cvat-ai/cvat/commits)

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

llama_index: an AI signed 0.2% of its commits, with Claude Code, Cursor, and GitHub Copilot; in cvat, 0.1%.

## Sources

- cvat-ai/cvat: Read on November 7, 2026, at commit 1a69829 (https://github.com/cvat-ai/cvat/tree/1a69829b80f7bb0438352ee4a66c84d93a1dd36b)
- 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.