Aser is equipped with standardized AI capability middleware, such as knowledge, memory, tracing, thinking, API interfaces, and social clients. By dynamically integrating Web3 toolkits, it helps developers quickly build and launch AI agents with native Web3 capabilities.

Website | Documentation | Get Support

Install from pypi:

pip3 install aser

Clone the repository:

git clone https://github.com/AmeNetwork/aser.git
cd aser
pip3 install -r requirements.txt

Please refer to .env.example file, and create a .env file with your own settings. You can use two methods to import environment variables.

Using python-dotenv:

pip install python-dotenv

Then add the following code to your python file.

from dotenv import load_dotenv
load_dotenv()

Exporting all variables in the terminal:

export $(grep -v '^#' .env | xargs)

from aser.agent import Agent
agent=Agent(name="aser agent",model="gpt-4.1-mini")
response=agent.chat("what's bitcoin?")
print(response)

Create a Discord AI Agent example

Create a Telegram AI Agent example

Create a Farcaster AI Agent example

Create an AI Agent with Memory example

Create an AI Agent with Knowledge example

Create an AI Agent with Tools example

Create an AI Agent with Toolkits example

Create an AI Agent with Trace example

Create an AI Agent with Model Smart Contract Protocol example

Create an AI Agent Server example

Create an AI Agent with CLI example

Create an AI Agent with Thinking example

Create an AI Agent with Swarms example

Create an AI Agent with MCP example

Create an AI Agent with Workflow example

Create an AI Agent with UI example