Observed arrival · 2026-10-12
OpenMoat puts a local policy between coding agents and your shell
An open-source local guard for Claude Code, Codex and Cursor that checks agent actions against allow, ask or deny rules.
○Open
⊠Login
$Paid
†Ads
✦Pretty
●Pro
◎Niche
◉Human
⚑Risk
ƒJS
- For
- Users of AI coding agents who want local command controls
- Worth noticing
- The example policy denies an agent-issued `moat allow --last` command under the `kernel-self` rule.
Field notes
The installation section offers Homebrew, shell, PowerShell and Cargo commands, followed by an instruction to run `moat init`. A policy table distinguishes routine work such as `npm test` from commands that prompt or receive a denial. The page links to a threat model and test results, and includes a route for reporting bypasses; those links are presented as resources, not independently verified here.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
○OpenPublic substance visible
✦PrettyNotable craft visible
●ProPolished or operationally mature
◎NicheUnusually specific use
One card from the complete issue