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

# OpenAI Agents SDK

> Drop-in code-execution tool for OpenAI Agents SDK.

## Install

```bash theme={null}
pip install podflare openai-agents
```

## Use

```python theme={null}
from agents import Agent, Runner
from podflare.integrations.openai_agents import podflare_code_interpreter

tool = podflare_code_interpreter()

agent = Agent(
    name="assistant",
    instructions="Use the run_code tool to answer computational questions.",
    tools=[tool],
)

result = await Runner.run(agent, "What is the sum of squares from 1 to 100?")
print(result.final_output)

# Cleanup the lazily-created Podflare sandbox
tool.close_podflare_sandbox()
```

## What the tool does

* On the first call, lazily creates a Podflare sandbox.
* On each invocation, calls `sandbox.run_code(code, language)`.
* Returns a dict with keys `stdout`, `stderr`, `exit_code`.
* The same sandbox is reused across invocations — Python REPL state
  persists, so the agent can build up state over a conversation.

## Options

```python theme={null}
tool = podflare_code_interpreter(
    host="https://api.podflare.ai",   # default: PODFLARE_HOSTD_URL env
    template="python-datasci",          # default: the primary pool
)
```

## Cleanup

The returned tool exposes a `close_podflare_sandbox()` method. Call it
after the agent run completes to destroy the VM.

<Tip>
  For many short-lived agent runs, creating a new sandbox per run is fine
  (pool hits are \~10 ms). For long-running conversations, reuse the same
  tool across turns to keep REPL state alive.
</Tip>