The-17/agentsecrets
Zero-knowledge secrets infrastructure built for AI agents to operate, not just consume.
This project helps AI agent developers secure sensitive API keys and credentials used by their AI agents. It stores these secrets, syncs them securely to the cloud, and injects them into agent requests without the agent ever seeing the actual credential value. This is used by developers building AI agents and services that need to interact with external APIs while maintaining high security.
Use this if you are developing AI agents and need a robust way to manage and use API keys or other credentials without exposing their values directly to the agent, even in memory.
Not ideal if your primary goal is general-purpose secrets management for human users or traditional applications, rather than specifically for AI agent workflows.
Stars
75
Forks
8
Language
Go
License
MIT
Category
Last pushed
Mar 26, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/The-17/agentsecrets"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
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...
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.
PunkGo/punkgo-jack
AI tool hook adapter for punkgo-kernel — every tool call gets a cryptographic receipt