jimmyracheta/AI-Runtime-Guard
Developer ProductivityA policy‑enforcing guard that blocks or approves every file and shell action performed by AI agents before they execute.
Features
- Blocks destructive commands (e.g., `rm -rf`) before execution
- Requires human approval for risky operations via local GUI or API
- Enforces workspace boundaries and per‑agent policy overlays
- Logs all actions to a persistent activity log and dashboard database
- Detects script‑laundering of blocked commands (Script Sentinel)
- Provides hardening hooks, sandboxing, and native tool restrictions where supported
Recent releases
View all 13 releases →
Review required
v2.3.0
Breaking risk
Auth
RBAC
RCE / SSRF
+1 more
Security hardening + UI fixes
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Install & Platforms
Install via
pipx
shell-script
Platforms
macos
linux
