What is Agent Guard?
Agent Guard is an AI-agent security tool that scans your local development environment for signals that can get AI coding accounts banned, then fixes them. It checks 20+ risk signals across shared environment factors and six per-product profiles — Claude Code, Cursor, Codex, Gemini, Windsurf, and Hermes — flagging issues like proxy leaks, timezone-versus-IP mismatches, shell configuration residue (for example HTTPS_PROXY or ANTHROPIC_BASE_URL in .zshrc), config leaks, and plaintext MCP API keys. Scanning is free and runs entirely on your machine, producing a red/yellow/green report with a score and file-level detail on each finding. The Pro version adds one-click auto-fix for supported items — timezone correction, shell proxy cleanup, agent config cleanup, and disabling auto-timezone — and it backs up original files to ~/.agent-guard/backups/ before any change so you can roll back. A newer runtime security guard adds continuous monitoring with 40+ safety rules. Agent Guard runs on macOS (Apple Silicon and Intel) and Windows. The free scan is available now; Pro auto-fix pricing is not published on the site.
What is Agent Guard used for?
Best for developers using Claude Code, Cursor, or Codex who want to check their local setup for account-ban risk signals.
How much does Agent Guard cost?
Pros and cons
Pros
- Detects 20+ risk signals across 6 product profiles (Claude Code, Cursor, Codex, Gemini, Windsurf, Hermes)
- Free scan runs entirely on your machine — nothing sent to the cloud
- Pro one-click auto-fix for timezone, shell proxy, and agent config, with backups to ~/.agent-guard/backups/
- Runtime security guard adds continuous monitoring with 40+ safety rules
Cons
- One-click auto-fix requires the paid Pro version
- Pro pricing is not published on the site
- Addresses ban-risk signals but cannot guarantee an account won't be banned
- Desktop-only (macOS and Windows); no Linux build listed
Questions about Agent Guard
What is Agent Guard used for?
Agent Guard is used to scan a developer's local AI-agent environment for signals that can trigger account bans — such as proxy leaks, timezone mismatches, config residue, and plaintext MCP keys — and to fix them.
Which AI agents does Agent Guard support?
Agent Guard has per-product compliance profiles for Claude Code, Cursor, Codex, Gemini, Windsurf, and Hermes, plus shared environment checks that apply to all agents.
Is Agent Guard free?
The environment scan and risk report are free and run locally. One-click auto-fix requires the Pro version; its pricing is not published on the site.
Does Agent Guard send my data to the cloud?
No. Agent Guard scans your environment locally and keeps all data on your machine; before any auto-fix, it backs up original files to ~/.agent-guard/backups/ so changes can be rolled back.
Reviews
Sign in to rate and review Agent Guard.
Sign in to reviewNo reviews yet. Be the first to review Agent Guard!