janee
CommunitySecret keys, injected safely by Janee.
Authorrsdouglas
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Janee addresses the risk of exposing API secrets to AI agents by acting as a local MCP-based proxy that injects credentials server-side and never reveals keys to agents.
Core Features & Use Cases
- Zero-knowledge agents: secrets never leave storage; credentials are injected per request.
- Audit and policy: full request audit trails with per-capability rules, TTLs, and ownership controls.
- Exec mode support: run whitelisted CLI tools with credentials injected via environment variables.
- Multi-agent and integration ready: works with GitHub, OpenAI, AWS services, and more, across stdio and HTTP transports.
Quick Start
Install Janee, run janee init to create a master key, add a service with janee add, and start the MCP server with janee serve so that agents can call execute() without ever seeing raw credentials.
Dependency Matrix
Required Modules
None requiredComponents
scripts
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: janee Download link: https://github.com/rsdouglas/janee/archive/main.zip#janee Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.