- Who it helps
- Developers adding email tools to agents.
- Availability
- MIT-licensed packages are described for Node.js, Python, PHP and Go. Hosted AgentiSend is a separate service.
Control repeated sends
The library describes rate limits, sending budgets, human holds and a kill switch. These controls can make repeated or excessive sends easier to catch in an application.
Know the enforcement boundary
Checks run inside the calling process. An agent able to edit that process can remove them. The default in-memory state is local to one process; shared deployments need an appropriate shared store.
What you can do
- Inspect every email-sending path and the state store before relying on the library’s limits. Open reference ↗
Where the evidence stops
No package was installed and no email was sent. Enforcement coverage and behavior under concurrency were not tested.
Sources read. Public source text read November 10, 2026 UTC. No installation, model inference or complete workflow executed.
Sources & further reading
GitHub · implementation
Agent Email Guard ↗
MIT library describes sending budgets, loop controls and in-process enforcement limits.
AgentiSend · page checked 2026-11-10
More sources reviewed (1)
Hacker News · discussion
New Show HN submissions ↗
First ten titles inspected; six explicitly concerned AI tools or agent-built artifacts.
Hacker News · page checked 2026-11-10
Coverage note: Independent execution and qualifying dated cross-platform attention remain incomplete.
The record over time (1)
Dated source checks and published explanations. An observation date can differ from the original release date.
- · Added to Current
Agent Email Guard is a library for checking automated email sends against budgets and loop limits.