Aser is equipped with standardized AI capability middleware, such as memory, RAG, MCP, CoT, API, and social clients. By dynamically integrating toolkits, it helps developers quickly build and launch AI agents.

Website | Documentation | Get Support | 中文

Install from pypi:

pip install aser

Or clone the repository:

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

Please refer to .env.example file, and create a .env file with your own settings. You don't need to configure all environment variables, just select the ones you use.

.env file example:

#MODEL
MODEL_BASE_URL=https://openrouter.ai/api/v1
MODEL_KEY=<your model key>

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

# Full configuration
aser = Agent(
    name="aser",
    model="gpt-4o-mini", 
    tools=[web3bio, exa], 
    knowledge=knowledge,
    memory=memory,
    chat2web3=[connector],
    mcp=[price],
    trace=trace
)

If you clone the project source code, before running the examples, please run pip install -e . in the root directory, which allows Python to find and import the aser module from the local source code. If you install it via pip install aser , you can run the examples directly.

Your First AI Agent example

Create an AI Agent with Model Config 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 Server example

Create an AI Agent with CLI example

Create a Discord AI Agent example

Create a Telegram AI Agent example

Create a Farcaster AI Agent example

Create an AI Agent with Chain of Thought example

Create an AI Agent with MCP example

Create an AI Agent with Workflow example

Create an AI Agent with UI example

Evaluate an AI Agent example

Router Multi-Agents example

Sequential Multi-Agents example

Parallel Multi-Agents example

Reactive Multi-Agents example

Hierarchical Multi-Agents example

Create an AI Agent with Model Smart Contract Protocol example