JSON for Agent

Store agent sessions and run history in local JSON files with JsonDb.

JsonDb stores an Agent's sessions and run history in local JSON files.

Usage

Start in a virtual environment and set the model key before running the example.

Set OpenAI Key

Set your OPENAI_API_KEY as an environment variable. You can get one from OpenAI.

export OPENAI_API_KEY=sk-***

Install the openai and ddgs packages:

uv pip install agno openai ddgs
json_for_agent.py
from agno.agent import Agent
from agno.db.json import JsonDb
from agno.models.openai import OpenAIChat
from agno.tools.websearch import WebSearchTools

db = JsonDb(db_path="tmp/json_db")

agent = Agent(
    model=OpenAIChat(id="gpt-5.2"),
    db=db,
    session_id="session_storage",
    tools=[WebSearchTools()],
    add_history_to_context=True,
    num_history_runs=3,
)
agent.print_response("How many people live in France?")
agent.print_response("What is their national anthem called?")
agent.print_response("What have we been talking about?")

Parameters

ParameterTypeDefaultDescription
idOptional[str]-Database ID. Derived deterministically from database path when omitted.
db_pathOptional[str]-Path to the directory where JSON files will be stored.
session_tableOptional[str]-Name of the JSON file to store sessions (without .json extension).
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 JSON file to store memories.
metrics_tableOptional[str]-Name of the JSON file to store metrics.
eval_tableOptional[str]-Name of the JSON file to store evaluation runs.
knowledge_tableOptional[str]-Name of the JSON file to store knowledge content.
traces_tableOptional[str]-Name of the JSON file to store traces.
spans_tableOptional[str]-Name of the JSON file to store spans.

Run the Example

Save the code as json_for_agent.py, complete the prerequisites above, then run:

python json_for_agent.py