lelu-auth/lelu
The authorization layer for AI Agents
Combines confidence-aware gating, prompt-injection filtering, and runtime risk evaluation in a layered decision pipeline—accounting for model uncertainty alongside traditional policy rules. Supports both YAML and Rego policy definitions with pluggable backends (SQLite for offline, PostgreSQL for production), plus JIT token scoping and human-in-the-loop review queues. Framework-agnostic SDKs for TypeScript, Python, and Go enable integration across diverse agent architectures.
9 stars and 1,015 monthly downloads. Available on npm.
Stars
9
Forks
—
Language
TypeScript
License
MIT
Category
Last pushed
Mar 21, 2026
Monthly downloads
1,015
Commits (30d)
0
Dependencies
5
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/lelu-auth/lelu"
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.
onecli/onecli
Open-source credential vault, give your AI agents access to services without exposing keys.
openleash/openleash
An open-source authorization layer where owners set policies, agents ask before acting, and...