> ## Documentation Index
> Fetch the complete documentation index at: https://docs.agno.com/llms.txt
> Use this file to discover all available pages before exploring further.
# Database
> Give your agents persistent storage for sessions, context, memory and knowledge.
Databases are a foundational part of agent engineering. Add a database to your agent and you get persistent storage for sessions, context, memory, learnings, and evaluation datasets.
* **Chat history.** Include previous messages in context for multi-turn conversations.
* **Session persistence.** Store session information and conversation history across requests.
* **State management.** Store internal agent state across runs. Critical for planning agents.
* **Context control.** Summarize, compress, enrich, and prune context for better responses.
* **Memory and knowledge.** Store user-level facts, searchable knowledge, decision traces, and learned insights.
* **Tracing and evaluation.** Store detailed traces for debugging, monitoring, and building evaluation datasets.
* **Data ownership.** No third-party dependencies. Query your own database. Build evaluation datasets, extract few-shot examples, flag low-quality responses for review.
This is how good software is built. Agents are no different.
## Quick Start
```python theme={null}
from agno.agent import Agent
from agno.db.sqlite import SqliteDb
agent = Agent(
db=SqliteDb(db_file="agent.db"),
add_history_to_context=True,
num_history_runs=3,
)
# First message
agent.print_response("I'm working on a Python API project", session_id="dev_session")
# Later — agent remembers the context
agent.print_response("What testing framework should I use?", session_id="dev_session")
```
The agent now persists sessions and includes the last 3 runs in every request.
## Guides
Include previous messages in context for multi-turn conversations.
Store and retrieve session data from your database.
Condense long conversations to manage token costs.
Choose what gets persisted to your database.
## Works With Teams and Workflows
Storage works identically across Agents, Teams, and Workflows:
```python theme={null}
from agno.team import Team
from agno.workflow import Workflow
from agno.db.postgres import PostgresDb
db = PostgresDb(db_url="postgresql://user:pass@localhost:5432/mydb")
team = Team(db=db, ...)
workflow = Workflow(db=db, ...)
```
## Supported Databases
Agno supports 13+ databases for session storage. Use SQLite for development, PostgreSQL for production. [View all supported databases](/database/providers/overview).
## Async Support
For async applications, use the async database classes:
```python theme={null}
from agno.agent import Agent
from agno.db.postgres import AsyncPostgresDb
agent = Agent(
db=AsyncPostgresDb(db_url="postgresql+psycopg_async://..."),
)
```
## Troubleshooting
You're using a synchronous engine with an async database class. Use `create_async_engine` from `sqlalchemy.ext.asyncio`.
You're using an async engine with a synchronous database class. Use `create_engine` from `sqlalchemy`.