hermes-labs-ai

hermes-labs-ai/agent-gorgon

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.

1 good first / help-wanted issue · Python · last activity Sep 29, 2026

3 stars 1 forks 3 watchers Python Apache License 2.0
agent-safety agent-security agent-skills ai-agents ai-observability ai-safety audit-logging defense-in-depth developer-tools forensics hermes-labs incident-response llm-security policy-enforcement process-monitoring python runtime-guard runtime-monitoring runtime-safety runtime-security
View on GitHub Website
1 Open Issue Need Help Last updated: Sep 29, 2026

Open Issues Need Help

View All on GitHub
Summarize the most recent Agent Gorgon audit run without requiring log-file hunting 24 days ago
help wanted good first issue
hermes-labs-ai/agent-gorgon
3

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.

Python
#agent-safety#agent-security#agent-skills#ai-agents#ai-observability#ai-safety#audit-logging#defense-in-depth#developer-tools#forensics#hermes-labs#incident-response#llm-security#policy-enforcement#process-monitoring#python#runtime-guard#runtime-monitoring#runtime-safety#runtime-security