Kern

Agent Tools

Equip agents with functions and toolkits for external actions.

Agents use tools to take actions and interact with external systems.

Tools are functions that an Agent can run to achieve tasks. For example: searching the web, running SQL, sending an email or calling APIs. You can use any python function as a tool or use a pre-built Kern toolkit.

The general syntax is:

1from kern.agent import Agent
2
3agent = Agent(
4    # Add functions or Toolkits
5    tools=[...],
6)

Tools can be a callable factory and are resolved at run time.

Using a Toolkit

Kern provides many pre-built toolkits that you can add to your Agents. For example, let's use the HackerNews toolkit to fetch tech news.

Tip

You can find more toolkits in the Toolkits guide.

Create News Agent

Create a file news_agent.py

1from kern.agent import Agent
2from kern.tools.hackernews import HackerNewsTools
3
4agent = Agent(tools=[HackerNewsTools()], markdown=True)
5agent.print_response("What are the top stories on HackerNews?", stream=True)

Run the agent

Install dependencies

1uv pip install openai kern-ai

Run the agent

1python news_agent.py

Writing your own Tools

For more control, write your own python functions and add them as tools to an Agent. For example, here's how to add a get_top_hackernews_stories tool to an Agent.

1import json
2import httpx
3
4from kern.agent import Agent
5
6def get_top_hackernews_stories(num_stories: int = 10) -> str:
7    """Use this function to get top stories from Hacker News.
8
9    Args:
10        num_stories (int): Number of stories to return. Defaults to 10.
11    """
12
13    # Fetch top story IDs
14    response = httpx.get('https://hacker-news.firebaseio.com/v0/topstories.json')
15    story_ids = response.json()
16
17    # Fetch story details
18    stories = []
19    for story_id in story_ids[:num_stories]:
20        story_response = httpx.get(f'https://hacker-news.firebaseio.com/v0/item/{story_id}.json')
21        story = story_response.json()
22        if "text" in story:
23            story.pop("text", None)
24        stories.append(story)
25    return json.dumps(stories)
26
27agent = Agent(tools=[get_top_hackernews_stories], markdown=True)
28agent.print_response("Summarize the top 5 stories on hackernews?", stream=True)

Read more about:

Developer Resources