Hello Agno!
I'm excited to introduce Agno - the fastest framework for building Multimodal Agents. Building Agents with Agno is as simple as:
from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno.tools.duckduckgo import DuckDuckGoTools
agent = Agent(
model=OpenAIChat(id="gpt-4o"),
tools=[DuckDuckGoTools()],
show_tool_calls=True,
markdown=True
)
agent.print_response("What's happening in France?", stream=True)
Why Agno?
Agno (ἁγνὸ) means pure in Greek, reflecting our design principles:
- Simplicity: No graphs, chains, or convoluted patterns – just pure Python.
- Uncompromising Performance: Blazing-fast Agents with a minimal memory footprint.
- Truly Agnostic: Any model, any provider, any modality – future-proof by design.
Blazing Fast
Agno outperforms all leading agent frameworks:
- 10000x Faster agent instantiation than Langgraph
- 50x Less Memory usage
In the video above, even though we give Langgraph a head start, Agno creates 2000 agents before Langgraph gets to 175. In this test, Agno was 11224x faster at creating Agents.
Get Started
We’re fully open-source – check out our GitHub repo and support us with a ⭐️
The future is one where every human, business, and government commands an army of Agents automating the mundane, freeing us up for more creative and enriching pursuits.
We’re excited to build this future with you 🧡