Squidbrake

Checks every AI agent tool call against rules, holds risky ones for human approval, logs an audit trail.

Servicefreeglobal

Squidbrake is a free, self-hosted safety layer that sits in front of AI coding and support agents (Claude Code, Cursor, Codex and others). It checks every tool call against a rules file, holds risky actions such as deletions or payments for a person to approve, and records every decision in a tamper-evident audit trail. It is aimed at developers and teams who want to let agents act autonomously without losing oversight.

Website

Full match profile

Behind the summary, Matchbox keeps a richer profile of Squidbrake - the signals our matcher actually reads to decide when to surface it. It stays private; claim the listing to see and control it.

Problem & pain-point mapping
Who we surface it to (audience fit)
What it's a strong alternative to
Trust & credibility signals

Claim Squidbrake to unlock →

Something wrong with this listing — dead link, not a real product, wrong info?

Try Matchbox with your own problem

Describe what is not working - we’ll show you whether Squidbrake (or something else) actually fits.

Try a problem