audit
01Command
Verify the llm-redact tamper-evident audit chain.
Large Language Model (LLM) information redactor that prevents private information from being sent to LLMs from agentic tools by substituting placeholders for private information on outgoing requests and then replaces the placeholders on the incoming responses seamlessly for the agentic tool users.
Command
Verify the llm-redact tamper-evident audit chain.
Command
Edit llm-redact config with the dashboard editor's guardrails: change rules, modes, deny strings, allowlists, NER, providers; validate; hot-reload.
Command
Show the effective llm-redact configuration (env overrides named).
Command
Run llm-redact's read-only diagnostics (config, build, vault, extras, posture).
Command
Display the llm-redact user guide (web UIs + plugin commands).
Command
Dry-run llm-redact detection on sample text — see exactly what would be redacted.
Command
Show the proxy's recent-request table: paths, providers, detections, status.
Command
List llm-redact vault sessions (id, token counts, last use).
Command
Show llm-redact proxy status: counters, detections by type, and the protection posture.
Command
List llm-redact named users and seats; guide invites and revokes.