Apply ordered allow/deny/ask policies to configured command shims and proxied HTTP traffic, with dry-run checks and JSONL audit logs.
Runtime policy guard for AI agent processes: watches process, file, and network activity from user space, applies deterministic policy, and attempts SIGSTOP or SIGKILL on reviewed triggers — no SDK required, works against any PID. Audit-only mode rehearses policy first; every decision logged as evidence.
Runtime budgets and automatic cancellation companion for pi-subagents
Continuous runtime guard and egress network firewall blocking secret leaks and policy violations.
Runtime defense toolkit against prompt injection for LLM APIs — intercepts, analyzes, and protects prompts in real-time
To associate your repository with the runtime-guard topic, visit your repo's landing page and select "manage topics."