Source: https://seerepo.com/compare/agent0ai/agent-zero/vs/run-llama/llama_index
Markdown source: https://seerepo.com/compare/agent0ai/agent-zero/vs/run-llama/llama_index.md
Description: agent-zero and llama_index share 25 technologies: OpenAI, AIOHTTP, starlette, anyio, cryptography, nltk, LangChain, litellm, MCP, sentence-transformers, tiktoken, lxml-html-clean, markdownify, newspaper3k, pypdf, unstructured, pillow, beautifulsoup4, html2text, pdf2image, pymupdf, Pydantic, boto3, psutil, and docker. Both are written in Python.

# agent-zero vs llama_index

agent-zero and llama_index share 25 technologies: OpenAI, AIOHTTP, starlette, anyio, cryptography, nltk, LangChain, litellm, MCP, sentence-transformers, tiktoken, lxml-html-clean, markdownify, newspaper3k, pypdf, unstructured, pillow, beautifulsoup4, html2text, pdf2image, pymupdf, Pydantic, boto3, psutil, and docker. Both are written in Python.

- [agent0ai/agent-zero](https://seerepo.com/r/agent0ai/agent-zero): Agent Zero AI framework
- [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: OpenAI, AIOHTTP, starlette, anyio, cryptography, nltk, LangChain, litellm, MCP, sentence-transformers, tiktoken, lxml-html-clean, markdownify, newspaper3k, pypdf, unstructured, pillow, beautifulsoup4, html2text, pdf2image, pymupdf, Pydantic, boto3, psutil, docker
- Only in agent-zero: Flask, a2wsgi, werkzeug, aiogram, uvicorn, fastmcp, Express, openai-whisper, langchain-community, faiss-cpu, kokoro, markdown, pytesseract
- Only in llama_index: aiomysql, aiosqlite, async-lru, asyncpg, azure-search-documents, azure-storage-blob, ibm-db, pgvecto-rs, pgvector, psycopg, psycopg2-binary, 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, graphql-core, tornado, Ray, soupsieve, tinycss2, ipywidgets, matplotlib-inline, prompt-toolkit, matplotlib, Rich, SQLAlchemy, argon2-cffi, azure-identity, Google, google-auth-httplib2, google-auth-oauthlib, pyjwt, msal, einops, firecrawl-py, guardrails-ai, llama-index-core, mem0ai, opencv-python, PaddlePaddle, tavily-python, torch, transformers, ibm-watsonx-ai, cohere, 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, bleach, markupsafe, mistune, nbformat, xlrd, bs4, defusedxml, jinja2, lxml, filetype, docx2txt, docling, markitdown, nbconvert, pdfplumber, 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, python-json-logger, Alibaba Cloud, OpenTelemetry

## Side by side

| | agent-zero | llama_index |
|---|---|---|
| Size | 294,924 lines written, 1,062 code files | 473,236 lines written, 2,055 code files |
| Who writes it | 1.2% of its commits signed by AI. With Claude Code, Codex, GitHub Copilot, and Cursor | 0.2% of its commits signed by AI. With Claude Code, Cursor, and GitHub Copilot |
| Activity | Last push November 5, 2026, 2,688 commits, 19,756 stars | Last push November 5, 2026, 7,963 commits, 52,820 stars |
| Tests | 277 test files. 30.3% 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, agent-zero or llama_index?

llama_index, with 473,236 lines written; agent-zero has 294,924.

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, agent-zero or llama_index?

llama_index, with 52,820 stars; agent-zero has 19,756.

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

### Which has more tests, agent-zero or llama_index?

llama_index, with 1,607 test files; agent-zero has 277.

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, agent-zero or llama_index?

Both got their last push on November 5, 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, agent-zero or llama_index?

agent-zero: an AI signed 1.2% of its commits, with Claude Code, Codex, GitHub Copilot, and Cursor; in llama_index, 0.2%.

The proof: [the commits each tool signed in agent0ai/agent-zero](https://seerepo.com/r/agent0ai/agent-zero/ai)

## Sources

- agent0ai/agent-zero: Read on November 5, 2026, at commit ba9b67d (https://github.com/agent0ai/agent-zero/tree/ba9b67df0f54ac78106ae85c552ef5d2458f7c9a)
- 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.