Hush
A secret store for AI agents: the agent never sees the plaintext.
Hush is a secret store for AI agents built around one rule: the agent never sees the plaintext. A secret is fetched once into the OS keychain, then injected into commands going forward, without ever passing through the model's context.
Source
Repository: https://github.com/royashbrook/hush
Maintain Hush?
Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.
[Hush on getagentictools](https://getagentictools.com/mcp/royashbrook-hush?ref=badge) Related mcp
Consulting Agents Enables Claude Code to consult with multiple expert coding agents powered by OpenAI's o3-mini and Claude 3.7 Sonnet for enhanced p
e18e Advises agents on modern and performant JavaScript package alternatives
gRPC Reflection Integrates with gRPC services using grpcurl, enabling method invocation, service listing, and description with custom header suppo
Render Deployment-related tooling for Render.com.
Currents Test Results Provides a bridge to Currents test results platform, enabling AI to analyze failing tests, optimize test suites, and troubleshoot
Attestix AI agent identity, W3C credentials, and EU AI Act compliance tools.