vettid/LEASH
LEASH — Lightweight Encrypted Agent Secret Handling. A proposed companion standard to MCP for secure, auditable, human-controlled secret access by AI agents.
This project helps operations engineers and security teams prevent data breaches by providing a secure way for AI agents to access sensitive credentials. It takes existing AI agent configurations that currently expose secrets and ensures those secrets never leave a secure vault, enabling human approval for every access request. The result is a secure, auditable method for agents to perform tasks without compromising sensitive data.
Use this if you are deploying AI agents that need to access API keys, database credentials, or other sensitive information, and you are concerned about those secrets being leaked or compromised.
Not ideal if your AI agents do not handle any sensitive data or require access to external tools with credentials.
Stars
7
Forks
1
Language
—
License
—
Category
Last pushed
Feb 10, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/vettid/LEASH"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
quantifylabs/aegis-memory
Secure context engineering for AI agents. Content security · integrity verification · trust...
kahalewai/dual-auth
Dual-Auth provides AGBAC dual-subject Authorization for AI Agents and Humans using existing IAM...
The-17/agentsecrets
Zero-knowledge secrets infrastructure built for AI agents to operate, not just consume.
stephnangue/warden
An identity-aware egress gateway that replaces cloud credentials with zero-trust access,...
onecli/onecli
Open-source credential vault, give your AI agents access to services without exposing keys.