io.github.azender1/safeagentdev-tools

safeagent

Verified · today

Exactly-once execution guard for AI agents. Prevents duplicate payments and webhooks on retry.

Install

claude mcp add safeagent -- uvx safeagent-exec-guard

Our take

SafeAgent is an execution guard for agent actions, aimed at deduping retries and producing durable receipts before real-world operations such as payments. It is more infrastructure primitive than plug-and-play app, with PostgreSQL-backed state and optional x402/payment extras. The owner has a couple of ecosystem forks, but I did not find default-branch self-insertion for SafeAgent.

reviewed by hand · 2026-07-06

Something wrong or dead here? Report it

Verification record

last verified: today
github stars: 6
last commit: today
archived: no
license: Apache-2.0
in registry since: 2026-06-17

github.com/azender1/SafeAgent