Async Sqlite for Team

Kern supports using Sqlite asynchronously as a storage backend for Teams, with the AsyncSqliteDb class.

Usage

You need to provide either db_url, db_file or db_engine. The following example uses db_file.

1"""
2Run: `uv pip install openai newspaper4k lxml_html_clean kern-ai sqlalchemy aiosqlite` to install the dependencies
3"""
4import asyncio
5from typing import List
6
7from kern.agent import Agent
8from kern.db.sqlite import AsyncSqliteDb
9from kern.models.openai import OpenAIResponses
10from kern.team import Team
11from kern.tools.hackernews import HackerNewsTools
12from kern.tools.hackernews import HackerNewsTools
13from pydantic import BaseModel
14
15# Initialize AsyncSqliteDb with a database file
16db = AsyncSqliteDb(db_file="team_storage.db")
17
18class Article(BaseModel):
19 title: str
20 summary: str
21 reference_links: List[str]
22
23hn_researcher = Agent(
24 name="HackerNews Researcher",
25 model=OpenAIResponses(id="gpt-5.2"),
26 role="Gets top stories from hackernews.",
27 tools=[HackerNewsTools()],
28)
29
30web_searcher = Agent(
31 name="Web Searcher",
32 model=OpenAIResponses(id="gpt-5.2"),
33 role="Searches the web for information on a topic",
34 tools=[HackerNewsTools()],
35 add_datetime_to_context=True,
36)
37
38hn_team = Team(
39 name="HackerNews Team",
40 model=OpenAIResponses(id="gpt-5.2"),
41 members=[hn_researcher, web_searcher],
42 db=db,
43 instructions=[
44 "First, search hackernews for what the user is asking about.",
45 "Then, ask the web searcher to search for each story to get more information.",
46 "Finally, provide a thoughtful and engaging summary.",
47 ],
48 output_schema=Article,
49 markdown=True,
50 show_members_responses=True,
51)
52
53asyncio.run(
54 hn_team.aprint_response("Write an article about the top 2 stories on hackernews")
55)

Params

ParameterTypeDefaultDescription
db_engineOptional[Engine]-The SQLAlchemy database engine to use.
db_urlOptional[str]-The database URL to connect to.
db_fileOptional[str]-The database file to connect to.
session_tableOptional[str]-Name of the table to store Agent, Team and Workflow sessions.
memory_tableOptional[str]-Name of the table to store user memories.
metrics_tableOptional[str]-Name of the table to store metrics.
eval_tableOptional[str]-Name of the table to store evaluation runs data.
knowledge_tableOptional[str]-Name of the table to store knowledge documents data.
traces_tableOptional[str]-Name of the table to store traces.
spans_tableOptional[str]-Name of the table to store spans.