Source: https://seerepo.com/compare/arc53/DocsGPT/vs/run-llama/llama_index
Markdown source: https://seerepo.com/compare/arc53/DocsGPT/vs/run-llama/llama_index.md
Description: DocsGPT and llama_index share 53 technologies: pgvector, psycopg, pyarrow, pymilvus, Redis, OpenAI, Google, ElevenLabs, AIOHTTP, anyio, starlette, soupsieve, matplotlib, prompt-toolkit, Rich, SQLAlchemy, google-auth-httplib2, pyjwt, cryptography, google-auth-oauthlib, msal, transformers, torch, fastembed, MCP, tiktoken, tokenizers, filetype, lxml, markupsafe, pillow, beautifulsoup4, markdownify, defusedxml, docling, pypdf, docx2txt, jinja2, pdf2image, pdfplumber, annotated-types, docling-core, jsonschema-specifications, marshmallow, pydantic-core, referencing, Pydantic, jsonschema, opentelemetry-api, opentelemetry-semantic-conventions, psutil, boto3, and OpenTelemetry. Both are written in Python.

# DocsGPT vs llama_index

DocsGPT and llama_index share 53 technologies: pgvector, psycopg, pyarrow, pymilvus, Redis, OpenAI, Google, ElevenLabs, AIOHTTP, anyio, starlette, soupsieve, matplotlib, prompt-toolkit, Rich, SQLAlchemy, google-auth-httplib2, pyjwt, cryptography, google-auth-oauthlib, msal, transformers, torch, fastembed, MCP, tiktoken, tokenizers, filetype, lxml, markupsafe, pillow, beautifulsoup4, markdownify, defusedxml, docling, pypdf, docx2txt, jinja2, pdf2image, pdfplumber, annotated-types, docling-core, jsonschema-specifications, marshmallow, pydantic-core, referencing, Pydantic, jsonschema, opentelemetry-api, opentelemetry-semantic-conventions, psutil, boto3, and OpenTelemetry. Both are written in Python.

- [arc53/DocsGPT](https://seerepo.com/r/arc53/DocsGPT): Private AI platform for agents, assistants and enterprise search. Built-in Agent Builder, Deep research, Document analysis, Multi-model support, and API connectivity for agents.
- [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: pgvector, psycopg, pyarrow, pymilvus, Redis, OpenAI, Google, ElevenLabs, AIOHTTP, anyio, starlette, soupsieve, matplotlib, prompt-toolkit, Rich, SQLAlchemy, google-auth-httplib2, pyjwt, cryptography, google-auth-oauthlib, msal, transformers, torch, fastembed, MCP, tiktoken, tokenizers, filetype, lxml, markupsafe, pillow, beautifulsoup4, markdownify, defusedxml, docling, pypdf, docx2txt, jinja2, pdf2image, pdfplumber, annotated-types, docling-core, jsonschema-specifications, marshmallow, pydantic-core, referencing, Pydantic, jsonschema, opentelemetry-api, opentelemetry-semantic-conventions, psutil, boto3, OpenTelemetry
- Only in DocsGPT: Flask, flask-restx, amqp, Milvus, obstore, psycopg-binary, psycopg-pool, s3transfer, Celery, Postgres, kombu, Hugging Face, Anthropic, Qdrant, asgiref, werkzeug, fastmcp, uvicorn, a2wsgi, React, Vite, react-router-dom, alembic, authlib, google-auth, itsdangerous, joserfc, oauthlib, requests-oauthlib, accelerate, faiss-cpu, rapidocr, safetensors, torchvision, gtts, onnxruntime, docling-slim, et-xmlfile, firecrawl-anydoc, latex2mathml, mako, markdown-it-py, mdurl, olefile, pdfminer.six, pylatexenc, uharfbuzz, xlsxwriter, pypdfium2, imageio, openpyxl, pytesseract, python-docx, python-pptx, reportlab, beartype, cel-python, email-validator, jsonschema-path, colorlog, loguru, opentelemetry-exporter-otlp-proto-grpc, opentelemetry-instrumentation, opentelemetry-instrumentation-aiohttp-client, opentelemetry-instrumentation-asgi, opentelemetry-instrumentation-celery, opentelemetry-instrumentation-flask, opentelemetry-instrumentation-logging, opentelemetry-instrumentation-psycopg, opentelemetry-instrumentation-redis, opentelemetry-instrumentation-requests, opentelemetry-instrumentation-sqlalchemy, opentelemetry-util-http, botocore, Gunicorn, daytona, styled-components, dompurify, markdown-it, prismjs, Tailwind CSS, class-variance-authority, tailwind-merge, Radix UI, reactflow, react-dropzone, Chart.js, Mermaid, react-chartjs-2, react-syntax-highlighter, @shadcn/react, cmdk, D3, react-day-picker, react-force-graph-2d, Lucide, react-markdown, unified, remark-gfm, micromark-util-character, micromark-util-types, micromark-util-symbol, unist-util-visit, rehype-katex, remark-math, remark-parse, remend
- Only in llama_index: aiomysql, aiosqlite, async-lru, asyncpg, azure-search-documents, azure-storage-blob, ibm-db, pgvecto-rs, psycopg2-binary, pyzmq, weaviate-client, lancedb, oracledb, DuckDB, SQLite, tablestore, chromadb, falkordb, MySQL, pinecone, clickhouse-connect, gcsfs, pyiceberg, pymochow, pymysql, pyobvector, s3fs, tcvectordb, typesense, graphql-core, tornado, Ray, tinycss2, ipywidgets, matplotlib-inline, argon2-cffi, azure-identity, einops, firecrawl-py, guardrails-ai, llama-index-core, mem0ai, opencv-python, PaddlePaddle, tavily-python, ibm-watsonx-ai, cohere, LangChain, sentence-transformers, dashscope, 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, bleach, mistune, nbformat, newspaper3k, xlrd, bs4, html2text, unstructured, pymupdf, lxml-html-clean, markitdown, nbconvert, pypdf2, tinytag, youtube-transcript-api, rfc3339-validator, prometheus-client, python-json-logger, docker, Alibaba Cloud

## Side by side

| | DocsGPT | llama_index |
|---|---|---|
| Size | 812,848 lines written, 1,275 code files | 473,236 lines written, 2,055 code files |
| Who writes it | 0.3% of its commits signed by AI. With Claude Code, GitHub Copilot, Codex, and Cursor | 0.2% of its commits signed by AI. With Claude Code, Cursor, and GitHub Copilot |
| Activity | Last push November 6, 2026, 5,882 commits, 18,360 stars | Last push November 5, 2026, 7,963 commits, 52,820 stars |
| Tests | 1,391 test files. 77.3% 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, DocsGPT or llama_index?

DocsGPT, with 812,848 lines written; llama_index has 473,236.

The proof: [arc53/DocsGPT's code at commit dcf08f1](https://github.com/arc53/DocsGPT/tree/dcf08f1b5a474b00d5981e00d1edb33529559571)

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

llama_index, with 52,820 stars; DocsGPT has 18,360.

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

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

llama_index, with 1,607 test files; DocsGPT has 1,391.

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, DocsGPT or llama_index?

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

The proof: [arc53/DocsGPT's commits on GitHub](https://github.com/arc53/DocsGPT/commits)

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

DocsGPT: an AI signed 0.3% of its commits, with Claude Code, GitHub Copilot, Codex, and Cursor; in llama_index, 0.2%.

## Sources

- arc53/DocsGPT: Read on November 6, 2026, at commit dcf08f1 (https://github.com/arc53/DocsGPT/tree/dcf08f1b5a474b00d5981e00d1edb33529559571)
- 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.