Story

I built a small Python library called SafeAgent that protects real-world side effects when AI agents retry tool calls.

One issue we ran into while experimenting with agent workflows is that retries can trigger irreversible actions multiple times:

agent calls tool ↓ network timeout ↓ agent retries ↓ side effect happens twice

Examples:

• duplicate payment • duplicate email • duplicate ticket • duplicate trade

Most systems solve this ad-hoc using idempotency keys scattered around different services.

SafeAgent centralizes this into a small execution guard.

The idea is simple:

1. every tool execution gets a request_id 2. SafeAgent records the execution receipt 3. retries return the original receipt instead of running the side effect again

Example:

FIRST CALL REAL SIDE EFFECT: sending email

SECOND CALL WITH SAME request_id SafeAgent returns the original execution receipt (no second side effect)

The project is early but includes examples for:

• OpenAI tool calls • LangChain style tools • CrewAI actions

PyPI: https://pypi.org/project/safeagent-exec-guard/

GitHub: https://github.com/azender1/SafeAgent

Curious how other people are handling retry safety for agent side effects.