#secrets

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

Save a secret: a small window opens that Claude cannot see, you paste there, it lands in 1Password. Read it back: any item in your vault loads into Claude with one fingerprint check, names only, never the values. Keys you paste in the chat are deleted before Claude reads them. Mac, Windows, Linux. MIT.

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.

Claude Code mod that redacts secrets and PII before the model reads them, stores placeholders in the conversation rows, and restores real values only inside file edits. No network, no model call.

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

Store API keys once in Windows Credential Manager and inject them only into the process that needs them. Built for coding agents (Codex, Claude Code).

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

Files AI agents can't touch — kernel-enforced no-read, read-only and append-only rules for Claude Code, Codex and any agent. macOS + Linux.

Security review skill for Claude Code, Codex and Opencode that reports only exploitable findings: every candidate goes through a separate refutation pass. Code, branch diffs, Kubernetes, Terraform, CI/CD, AI agents.

A privacy layer for Claude Code: names, emails, addresses and API keys are swapped for placeholders before the model sees them

Claude Code mod: guardrails for kubectl, helm, terraform and Kubernetes Secrets — named targets, script checks, plan gate, audit, and Secret values the model never sees

Never give AI companies your secrets! A local LLM-based privacy filter for LLM users. Seamless integration with your existing AI tools as a Python library / OpenAI SDK replacement / API Gatetway / Web Server.