#secrets

A simple MacOS helper for safer exposure of secrets to your agents

Offline, no-AI "safe to ship?" gate for vibe-coded apps — finds the security mistakes AI coding agents make (secrets, unprotected routes, eval-RCE, SQLi, CORS, JWT, leaked keys). CLI + MCP, agent-runnable.

seatbelt for my pi.dev agent: blocks secret-file access, redacts creds from output, blocks egress + git leaks.

Open-source AI Security Gateway that sanitizes secrets, PII, and internal context before prompts reach external LLMs.

Local-first CLI to snapshot, scrub, and migrate your Claude Code setup — settings, MCP servers, subagents, and skills — as a redacted, portable profile.

Move plaintext secrets into a 1claw local vault and wire your AI agents to use them without ever seeing the values.