HOL Guard

Verified

Local approvals for AI coding agent actions: HOL Guard holds risky shell commands, secret reads, MCP calls and installs until you say yes.

Visit

Promoted

Community intelligence. Know your members. Increase engagement

Platform that provides an insight to increase engagement of your community

51 upvotes

ConsentScope

See what websites do before you consent

50 upvotes

Pateches Game

Patches.cafe is a free browser puzzle about fitting numbered rectangles together. It looks like a small sewing project and plays like a tidy piece of spatial re

49 upvotes

Beautiful Screenshots - Lustly

Turn any webpage into a screenshot worth sharing

45 upvotes

Buy your first business like a fund would.

The acquisition CRM and off-market sourcing engine for people buying small businesses.

44 upvotes

About

Coding agents move fast: a single session can run shell commands, read .env files, call MCP servers and install packages. HOL Guard is local-first runtime control for that work. It runs on your machine next to Claude Code, Codex and Cursor, checks each action against your policy, and holds the risky ones until you approve or deny them, while ordinary edits keep flowing. Local HOL Guard is free and open source under Apache-2.0; Guard Cloud is an optional paid add-on for teams that want shared policy. Get started: pipx install hol-guard && hol-guard init HOL Guard is not a gateway or a network firewall, and it does not claim to block every prompt injection. Built by HOL.