Skip to main content
Hypertic is the fastest and easiest way to build AI agents that can use any large language model, tools, and knowledge bases, while maintaining context and handling complex tasks. Here are some of the key features of Hypertic:

Tools & MCP

Create custom tools with Python functions or connect to MCP servers.

Memory & Context

Store conversation history and maintain context between interactions.

Model Agnostic

Switch between OpenAI, Anthropic, Google, and others without changing your code.

Knowledge Base

Build agents that can search and use your documents and knowledge bases.

​
Why Hypertic?

Hypertic is built on the idea that building AI agents should be straightforward. The framework provides a clean way to build agents with models, tools, memory, and context. There’s no hidden complexity or magic. Just Python code that does what you expect. You get full control when you need it. Sensible defaults get you started quickly, and you can customize everything about your agents.

​
Example

Here’s an example of an Agent that uses a tool and manages conversation history: 
from hypertic import Agent
from hypertic.tools import Calculator, FileReader

# Define a custom tool
def get_weather(city: str) -> str:
    """Get weather for a city."""
    return f"Sunny, 72°F in {city}"

# Create agent with tools
agent = Agent(
    model="gpt-4",
    tools=[Calculator(), FileReader(), get_weather],
    system_prompt="You are a helpful assistant.",
)

# Use it
result = agent.run("Calculate 15% of 240, then tell me the weather in SF")
print(result)
If you’re new to Hypertic, follow the quickstart to build your first Agent or explore the examples to see the framework in action.