> ## Documentation Index
> Fetch the complete documentation index at: https://docs.mirage.strukto.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Agno

> Give Agno agents shell-based filesystem access to any Mirage workspace using MirageToolkit.

[Agno](https://github.com/agno-agi/agno) is an agent framework that groups related tools into `Toolkit` classes. Mirage ships `MirageToolkit`, a toolkit that runs Mirage's seven tools in a workspace instead of on the host.

## Install

```bash theme={null}
uv add 'mirage-ai[agno]'
```

## Usage

```python theme={null}
import asyncio

from agno.agent import Agent
from agno.models.openai import OpenAIChat

from mirage import MountMode, RAMVFS, Workspace
from mirage.agents.agno import MirageToolkit

ws = Workspace({"/data": RAMVFS()}, mode=MountMode.WRITE)

agent = Agent(
    model=OpenAIChat(id="gpt-5.4-mini"),
    tools=[MirageToolkit(ws)],
    instructions=("You have access to a virtual filesystem via shell "
                  "tools. Use them to explore and read files."),
    markdown=True,
)


async def main() -> None:
    await ws.shell('echo "hello from mirage" | tee /data/hello.txt')
    await agent.aprint_response(
        "List all files under /data and show the contents of each one.")


asyncio.run(main())
```

## Tools

The toolkit serves the session's seven tools, [`session.tools`](/python/access/in-app#session-tools), as far as the session's profile leaves them (`session.tools.names()`), each as a sync and async pair under one name: Agno calls the async one in `arun` and `aprint_response`, and the sync one otherwise.

## Exports

| Symbol | Purpose |
| - | - |
| `MirageToolkit` | Agno `Toolkit` exposing Mirage's seven tools, backed by the shared tool table. |
| `MIRAGE_SYSTEM_PROMPT` | Default system prompt describing the virtual filesystem. |
| `build_system_prompt` | Compose the default prompt with mount info and extra instructions. |

## Examples

* [`examples/python/agents/agno/agno_example.py`](https://github.com/strukto-ai/mirage/blob/main/examples/python/agents/agno/agno_example.py), `Agent` with `MirageToolkit` over a RAM workspace, sync and async.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.