← CookbookView source on GitHub ↗

Agno Agents

Banner

This folder has the following agents:

Tech Stack

Prerequisites

Installation

1. Get the code

git   clone    https://github.com/nebius/token-factory-cookbook/
cd    agents/agno-agents-examples

2. Install dependencies:

using uv

# create a venv and install dependencies
uv  sync

# install a kernel
source  .venv/bin/activate
python -m ipykernel install --user --name="cookbook-1" --display-name "cookbook-1"
# select this kernel in Jupyter

Or install using python pip

pip install -r requirements.txt
python -m ipykernel install --user --name="cookbook-1" --display-name "cookbook-1"
# select this kernel in Jupyter

3 - Create .env file

Create a .env file in the project root and add your Nebius API key:

cp env.example .env
NEBIUS_API_KEY=your_api_key_here

Running the agents

Using uv

uv run --with jupyter jupyter lab

using python/pip

jupyter lab

Open the notebooks in Jupyter - select the kernel we defined earlier - run the notebook

Agents

Web search agent

Uses duckduckgo to search the web

agno_websearch_agent.ipynb

  1. Creating an agent with a knowledge base for specialized domains
  2. Building multi-agent systems where specialized agents work together

Multi Agent System

This example shows how mutiple agents work togethe.

  1. A web search agent for finding general information
  2. A finance agent for retrieving financial data
  3. A coordinator agent that delegates tasks to the specialized agents

agno_multi_agent.ipynb

Knowledgebase Agent

This example demonstrates how to create an agent with specialized knowledge. Use couchbase as vector database.

Prerequisites

COUCHBASE_USER=username
COUCHBASE_PASSWORD=password
COUCHBASE_CONNECTION_STRING=

agno_knowledgebase_agent.ipynb

References and Acknowledgements