🧠 Persistent memory + 🔍 session search + 🛡️ secret scanning for Pi. Token-aware policy-only memory by default, SQLite FTS5 search, auto-consolidation, procedural skills. 368 tests. Ported from Hermes agent.
Scan source code for secrets, credentials, and PII
Codex skill for inspecting and triaging GitHub security alerts.
Local-first MCP server that scans developer prompts for secrets, PII, and cost before they hit the LLM.
Stop secrets before they leak — pre-commit hook, git history audit, live API verification, 44 credential patterns
OpsContext for AI Agents — read-only fleet visibility (PM2/nginx/Docker/git/cron) + tamper-evident audit log + policy-as-code hooks. The ops + compliance layer Claude Code can't grow natively.