SurrealDB for Team

Store team sessions and run history in SurrealDB with SurrealDb.

SurrealDb stores a Team's sessions and run history in SurrealDB.

Usage

Start in a virtual environment.

Install dependencies:

uv pip install agno sqlalchemy anthropic surrealdb ddgs

Run SurrealDB

Install Docker Desktop, then start SurrealDB on port 8000:

docker run --rm --pull always -p 8000:8000 surrealdb/surrealdb:latest start --user root --pass root

This development server uses temporary storage. Its data is lost when the server stops. To retain data across server or container replacement, configure a mounted volume and an on-disk backend as described in the SurrealDB Docker guide.

Set your Anthropic API key:

export ANTHROPIC_API_KEY="your_anthropic_api_key_here"
surrealdb_for_team.py
from typing import List

from agno.agent import Agent
from agno.db.surrealdb import SurrealDb
from agno.models.anthropic import Claude
from agno.team import Team
from agno.tools.hackernews import HackerNewsTools
from agno.tools.websearch import WebSearchTools
from pydantic import BaseModel

SURREALDB_URL = "ws://localhost:8000"
SURREALDB_USER = "root"
SURREALDB_PASSWORD = "root"
SURREALDB_NAMESPACE = "agno"
SURREALDB_DATABASE = "surrealdb_for_team"

credentials = {"username": SURREALDB_USER, "password": SURREALDB_PASSWORD}
db = SurrealDb(
    client=None,
    db_url=SURREALDB_URL,
    db_creds=credentials,
    db_ns=SURREALDB_NAMESPACE,
    db_db=SURREALDB_DATABASE,
)


class Article(BaseModel):
    title: str
    summary: str
    reference_links: List[str]


hn_researcher = Agent(
    name="HackerNews Researcher",
    model=Claude(id="claude-sonnet-4-5-20250929"),
    role="Gets top stories from HackerNews.",
    tools=[HackerNewsTools()],
)

web_searcher = Agent(
    name="Web Searcher",
    model=Claude(id="claude-sonnet-4-5-20250929"),
    role="Searches the web for information on a topic",
    tools=[WebSearchTools()],
    add_datetime_to_context=True,
)

hn_team = Team(
    name="HackerNews Team",
    model=Claude(id="claude-sonnet-4-5-20250929"),
    members=[hn_researcher, web_searcher],
    db=db,
    instructions=[
        "First, search HackerNews for what the user is asking about.",
        "Then, ask the web searcher to search for each story to get more information.",
        "Finally, summarize each story and include its reference links.",
    ],
    output_schema=Article,
    markdown=True,
    show_members_responses=True,
)

hn_team.print_response("Write an article about the top 2 stories on HackerNews")

Run the example

Save the code as surrealdb_for_team.py, start the database described above, and run:

python surrealdb_for_team.py

Parameters

ParameterTypeDefaultDescription
idOptional[str]-Database ID. Derived deterministically from db_url and db_db when omitted.
clientOptional[Union[BlockingWsSurrealConnection, BlockingHttpSurrealConnection]]-A blocking connection, either HTTP or WebSocket.
db_urlstr-The SurrealDB connection URL.
db_credsdict[str, str]-Database credentials dictionary (username, password).
db_nsstr-The SurrealDB namespace to use.
db_dbstr-The SurrealDB database name to use.
session_tableOptional[str]-Name of the table to store Agent, Team and Workflow sessions.
runs_tableOptional[str]NoneStorage name for individual runs. Defaults to agno_runs, or <session_table>_runs when a custom session name is supplied.
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.