A series of AI agents built using the Agno framework
This project uses uv for Python dependency management.
- Python 3.12+
- uv package manager
- OpenAI API key
We use uv for python environment and package management. Install it by following the the uv documentation or use the command below for unix-like systems:
curl -LsSf https://astral.sh/uv/install.sh | sh-
Clone the repository
-
Setup your virtual environment:
uv venv --python 3.12 source .venv/bin/activate -
Install dependencies:
uv sync
Set your OpenAI API key as an environment variable:
export OPENAI_API_KEY=="your-oepnai-api-key"This project uses black for code formatting and isort for import sorting, both configured in pyproject.toml.
Format code and sort imports (recommended):
uv run black . && uv run isort .Check formatting and import sorting without making changes:
uv run black --check . && uv run isort --check-only .Show formatting and import sorting diff without making changes:
uv run black --diff . && uv run isort --diff .Run the different agent levels:
Level 1: Agents with tools and instructions
uv run python agent/sample/level_1_agent.pyLevel 2: Agents with knowledge and storage
uv run python agent/sample/level_2_agent.pyLevel 3: Agents with memory and reasoning
uv run python agent/sample/level_3_agent.pyLevel 4: Agent Teams that can reason and collaborate
uv run python agent/sample/level_4_team.pyLevel 5: Agentic Workflows with state and determinism
uv run python agent/sample/level_5_workflow.pyRun Research Agent
uv run python agent/sample/research_agent.pyRun Playground Server Locally
uv run python playground/playground.pyagent/- Contains all agent implementationssample/- Sample agent implementations demonstrating different levels and featureshealthcare/- Healthcare Agent MVP implementationmemory/- Memory management examplessession_state/- Session state management examplestool/- Custom tool implementations
playground/- Contains playground serverpyproject.toml- Project configuration and dependencies.python-version- Python version specification