Agno is a lightweight framework for building Agents with memory, knowledge, tools and reasoning.
Use Agno to build Reasoning Agents, Multimodal Agents, Teams of Agents and Agentic Workflows.
Here's an Agent that writes a financial report by reasoning through each step:
from agno.agent import Agent
from agno.models.anthropic import Claude
from agno.tools.reasoning import ReasoningTools
from agno.tools.yfinance import YFinanceTools
agent = Agent(
model=Claude(id="claude-3-7-sonnet-latest"),
tools=[
ReasoningTools(add_instructions=True),
YFinanceTools(stock_price=True, analyst_recommendations=True, company_info=True, company_news=True),
],
instructions=[
"Use tables to display data",
"Only output the report, no other text",
],
markdown=True,
)
agent.print_response("Write a report on NVDA", stream=True, show_full_reasoning=True, stream_intermediate_steps=True)reasoning_finance_agent.mp4
Agno is simple, fast and model-agnostic. Here are some key features:
- Model Agnostic: Agno provides a unified interface for 23+ model providers, no lock-in.
- Lightning Fast: Agents instantiate 10,000x faster than LangGraph and use 50x less memory (benchmarks).
- First class support for Reasoning: Build Agents that can "think" and "analyze" using Reasoning Models, Reasoning Tools or our custom
CoT+Tool-useapproach (see this example). - Natively Multi Modal: Agents can take in text, image, audio and video and generate text, image, audio and video as output.
- Advanced Multi Agent Architecture: Industry leading multi-agent architecture with 3 different modes:
route,collaborateandcoordinate. - Long-term Memory: Built in support for long-term memory with our
StorageandMemoryclasses. - 20+ Vector Databases for Knowledge: Add domain knowledge to your Agents by integrating with 20+ vector databases. Fully async and highly performant.
- Structured Outputs: First class support for structured outputs using native structured outputs or
json_mode. - Monitoring: Track agent sessions and performance in real-time on agno.com.
- Start by building your first Agent
- Check out the examples
- Read the documentation
pip install -U agnoAgents are intelligent programs that solve problems autonomously.
Agents can reason, have memory, domain knowledge and the ability to use tools (like searching the web, querying a database, making API calls). Unlike traditional programs that follow a predefined execution path, Agents dynamically adapt their approach based on the context and tool results.
Instead of a rigid binary definition, let's think of Agents in terms of agency and autonomy.
- Level 0: Agents with no tools (basic inference tasks).
- Level 1: Agents with tools for autonomous task execution.
- Level 2: Agents with knowledge, combining memory and reasoning.
- Level 3: Teams of specialized agents collaborating on complex workflows.
Let's start with a Reasoning Agent so we get a sense of Agno's capabilities.
Save this code to a file: reasoning_agent.py.
from agno.agent import Agent
from agno.models.anthropic import Claude
from agno.tools.reasoning import ReasoningTools
from agno.tools.yfinance import YFinanceTools
agent = Agent(
model=Claude(id="claude-3-7-sonnet-latest"),
tools=[
ReasoningTools(add_instructions=True, add_few_shot=True),
YFinanceTools(
stock_price=True,
analyst_recommendations=True,
company_info=True,
company_news=True,
),
],
instructions=[
"Use tables to display data",
"Only output the report, no other text",
],
markdown=True,
)
agent.print_response(
"Write a report on NVDA",
stream=True,
show_full_reasoning=True,
stream_intermediate_steps=True,
)Then create a virtual environment, install dependencies, export your ANTHROPIC_API_KEY and run the agent.
uv venv --python 3.12
source .venv/bin/activate
uv pip install agno anthropic yfinance
export ANTHROPIC_API_KEY=sk-ant-api03-xxxx
python reasoning_agent.pyWe can see the Agent is reasoning through the task, using the ReasoningTools and YFinanceTools to gather information. This is how the output looks like:
reasoning_finance_agent.mp4
Now let's walk through the simple -> tools -> knowledge -> teams of agents flow.
The simplest Agent is just an inference task, no tools, no memory, no knowledge.
from agno.agent import Agent
from agno.models.openai import OpenAIChat
agent = Agent(
model=OpenAIChat(id="gpt-4o"),
description="You are an enthusiastic news reporter with a flair for storytelling!",
markdown=True
)
agent.print_response("Tell me about a breaking news story from New York.", stream=True)To run the agent, install dependencies and export your OPENAI_API_KEY.
pip install agno openai
export OPENAI_API_KEY=sk-xxxx
python basic_agent.pyView this example in the cookbook
This basic agent will obviously make up a story, lets give it a tool to search the web.
from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno.tools.duckduckgo import DuckDuckGoTools
agent = Agent(
model=OpenAIChat(id="gpt-4o"),
description="You are an enthusiastic news reporter with a flair for storytelling!",
tools=[DuckDuckGoTools()],
show_tool_calls=True,
markdown=True
)
agent.print_response("Tell me about a breaking news story from New York.", stream=True)Install dependencies and run the Agent:
pip install duckduckgo-search
python agent_with_tools.pyNow you should see a much more relevant result.
View this example in the cookbook
Agents can store knowledge in a vector database and use it for RAG or dynamic few-shot learning.
Agno agents use Agentic RAG by default, which means they will search their knowledge base for the specific information they need to achieve their task.
from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno.embedder.openai import OpenAIEmbedder
from agno.tools.duckduckgo import DuckDuckGoTools
from agno.knowledge.pdf_url import PDFUrlKnowledgeBase
from agno.vectordb.lancedb import LanceDb, SearchType
agent = Agent(
model=OpenAIChat(id="gpt-4o"),
description="You are a Thai cuisine expert!",
instructions=[
"Search your knowledge base for Thai recipes.",
"If the question is better suited for the web, search the web to fill in gaps.",
"Prefer the information in your knowledge base over the web results."
],
knowledge=PDFUrlKnowledgeBase(
urls=["https://agno-public.s3.amazonaws.com/recipes/ThaiRecipes.pdf"],
vector_db=LanceDb(
uri="tmp/lancedb",
table_name="recipes",
search_type=SearchType.hybrid,
embedder=OpenAIEmbedder(id="text-embedding-3-small"),
),
),
tools=[DuckDuckGoTools()],
show_tool_calls=True,
markdown=True
)
# Comment out after the knowledge base is loaded
if agent.knowledge is not None:
agent.knowledge.load()
agent.print_response("How do I make chicken and galangal in coconut milk soup", stream=True)
agent.print_response("What is the history of Thai curry?", stream=True)Install dependencies and run the Agent:
pip install lancedb tantivy pypdf duckduckgo-search
python agent_with_knowledge.pyView this example in the cookbook
Agents work best when they have a singular purpose, a narrow scope and a small number of tools. When the number of tools grows beyond what the language model can handle or the tools belong to different categories, use a team of agents to spread the load.
from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno.tools.duckduckgo import DuckDuckGoTools
from agno.tools.yfinance import YFinanceTools
from agno.team import Team
web_agent = Agent(
name="Web Agent",
role="Search the web for information",
model=OpenAIChat(id="gpt-4o"),
tools=[DuckDuckGoTools()],
instructions="Always include sources",
show_tool_calls=True,
markdown=True,
)
finance_agent = Agent(
name="Finance Agent",
role="Get financial data",
model=OpenAIChat(id="gpt-4o"),
tools=[YFinanceTools(stock_price=True, analyst_recommendations=True, company_info=True)],
instructions="Use tables to display data",
show_tool_calls=True,
markdown=True,
)
agent_team = Team(
mode="coordinate",
members=[web_agent, finance_agent],
model=OpenAIChat(id="gpt-4o"),
success_criteria="A comprehensive financial news report with clear sections and data-driven insights.",
instructions=["Always include sources", "Use tables to display data"],
show_tool_calls=True,
markdown=True,
)
agent_team.print_response("What's the market outlook and financial performance of AI semiconductor companies?", stream=True)Install dependencies and run the Agent team:
pip install duckduckgo-search yfinance
python agent_team.pyView this example in the cookbook
We're thrilled to announce a month long, open source AI Agent Hackathon β open to all builders and dreamers working on agents, RAG, tool use, and multi-agent systems.
We're giving away $20,000 in prizes for the most ambitious Agent projects
- π 10 winners: $300 each
- π₯ 10 winners: $500 each
- π₯ 5 winners: $1,000 each
- π₯ 1 winner: $2,000
- π GRAND PRIZE: $5,000 π
Follow this post for more details and updates
If you're building in the AI Agent space, or want to help shape the next generation of Agent builders - we'd love to work with you.
Reach out to [email protected] to get involved.
At Agno, we're obsessed with performance. Why? because even simple AI workflows can spawn thousands of Agents to achieve their goals. Scale that to a modest number of users and performance becomes a bottleneck. Agno is designed to power high performance agentic systems:
- Agent instantiation: ~2ΞΌs on average (~10,000x faster than LangGraph).
- Memory footprint: ~3.75Kib on average (~50x less memory than LangGraph).
Tested on an Apple M4 Mackbook Pro.
While an Agent's run-time is bottlenecked by inference, we must do everything possible to minimize execution time, reduce memory usage, and parallelize tool calls. These numbers may seem trivial at first, but our experience shows that they add up even at a reasonably small scale.
Let's measure the time it takes for an Agent with 1 tool to start up. We'll run the evaluation 1000 times to get a baseline measurement.
You should run the evaluation yourself on your own machine, please, do not take these results at face value.
# Setup virtual environment
./scripts/perf_setup.sh
source .venvs/perfenv/bin/activate
# OR Install dependencies manually
# pip install openai agno langgraph langchain_openai
# Agno
python evals/performance/instantiation_with_tool.py
# LangGraph
python evals/performance/other/langgraph_instantiation.pyThe following evaluation is run on an Apple M4 Mackbook Pro. It also runs as a Github action on this repo.
LangGraph is on the right, let's start it first and give it a head start.
Agno is on the left, notice how it finishes before LangGraph gets 1/2 way through the runtime measurement, and hasn't even started the memory measurement. That's how fast Agno is.
agno_vs_langgraph_perf.mp4
Dividing the average time of a Langgraph Agent by the average time of an Agno Agent:
0.020526s / 0.000002s ~ 10,263
In this particular run, Agno Agents startup is roughly 10,000 times faster than Langgraph Agents. The numbers continue to favor Agno as the number of tools grow, and we add memory and knowledge stores.
To measure memory usage, we use the tracemalloc library. We first calculate a baseline memory usage by running an empty function, then run the Agent 1000x times and calculate the difference. This gives a (reasonably) isolated measurement of the memory usage of the Agent.
We recommend running the evaluation yourself on your own machine, and digging into the code to see how it works. If we've made a mistake, please let us know.
Dividing the average memory usage of a Langgraph Agent by the average memory usage of an Agno Agent:
0.137273/0.002528 ~ 54.3
Langgraph Agents use ~50x more memory than Agno Agents. In our opinion, memory usage is a much more important metric than instantiation time. As we start running thousands of Agents in production, these numbers directly start affecting the cost of running the Agents.
Agno agents are designed for performance and while we do share some benchmarks against other frameworks, we should be mindful that accuracy and reliability are more important than speed.
We'll be publishing accuracy and reliability benchmarks running on Github actions in the coming weeks. Given that each framework is different and we won't be able to tune their performance like we do with Agno, for future benchmarks we'll only be comparing against ourselves.
When building Agno agents, using Agno documentation as a source in Cursor is a great way to speed up your development.
- In Cursor, go to the settings or preferences section.
- Find the section to manage documentation sources.
- Add
https://docs.agno.comto the list of documentation URLs. - Save the changes.
Now, Cursor will have access to the Agno documentation.
- Docs: docs.agno.com
- Getting Started Examples: Getting Started Cookbook
- All Examples: Cookbook
- Community forum: community.agno.com
- Chat: discord
We welcome contributions, read our contributing guide to get started.
Agno logs which model an agent used so we can prioritize updates to the most popular providers. You can disable this by setting AGNO_TELEMETRY=false in your environment.
