LlamaIndex at a glance

LlamaIndex pairs its document parsing and retrieval tools with event-driven Agent Workflows in Python and TypeScript. Workflows can pause for human input, persist state, and be served as MCP servers or deployed to LlamaCloud.

Best for: Document-heavy, retrieval-centred agents that parse, extract and search before they act.

Key facts

Maintainer

LlamaIndex

Languages

Python, TypeScript

Licence

MIT

Latest version

llama-index 0.14.25 / llama-index-workflows 2.25.0 · September 25, 2026

Repository

run-llama/llama_index · 52,380 stars

Hosted option

LlamaCloud via LlamaAgents (llamactl deploy)

Deploy with llamactl; workflows are then served from api.cloud.llamaindex.ai.

Quickstart

Install the package, set the credentials, then run the smallest agent from the official docs. Model IDs are the ones the docs use and may not be enabled on your account.

pip install llama-index-core llama-index-llms-openai  (from search summary of the starter tutorial; not copied verbatim)

Needs OPENAI_API_KEY

import asyncio
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Define a simple calculator tool
def multiply(a: float, b: float) -> float:
    """Useful for multiplying two numbers."""
    return a * b

# Create an agent workflow with our calculator tool
agent = FunctionAgent(
    tools=[multiply],
    llm=OpenAI(model="gpt-4o-mini"),
    system_prompt="You are a helpful assistant that can multiply two numbers.",
)

async def main():
    # Run the agent
    response = await agent.run("What is 1234 * 4567?")
    print(str(response))

# Run the agent
if __name__ == "__main__":
    asyncio.run(main())

Quickstart source

Features

Recent changes

• The workflows repo was renamed run-llama/llama-agents (LlamaAgents); the PyPI package is still llama-index-workflows.
• llamactl now serves and deploys workflows.

Alternatives in the same language