Security●●Solid
Lelu – catch AI agents when they're manipulated at runtime
Okta for who can access, Lelu for when agents are being manipulated.
Big BrainNiche Gem
Abenezer0923
2017h ago
Back to browse
GitHub Repository
Open source authorization engine for AI agents. Confidence-aware gating · Human-in-the-loop review · Policy-as-code · Full audit trail
32 starsTypeScript
Lelu – authorization engine that catches manipulated AI agents
by Abenezer0923·Jun 20, 2026·4 points·0 comments
AI Analysis
●●SolidSlickSolve My Problem
Four decision outcomes including compute redirect—prompt injection detected before policy runs.
Strengths
- •Four outcomes (allow, deny, human_review, compute) beat binary allow/deny
- •SDKs for Python and npm with local SQLite demo—no cloud account needed
- •25 stars and active issues show real engagement and iteration
Weaknesses
- •Authorization for AI agents is emerging but getting competitive fast
- •16 open issues suggests stability questions for production use
Category
Target Audience
Teams deploying AI agents with privileged access
Similar To
OPA · Casbin · AWS Verified Permissions
Similar Projects
Developer Tools●●●Banger
Rigour – Open-source quality gates for AI coding agents
AST-verified AI code audits prevent hallucinations; LLM findings checked against parser ground truth.
Big BrainSolve My ProblemSlick
erashu212
214mo ago
Security●●Solid
Agent Gate – Execution authority for AI agents, vault-backed rollback
The idea of inserting a deterministic 'gate' between proposed tool calls and execution is smart and practical: precomputed classification plus an agent-unreachable vault means destructive operations become reversible by default. The README calls out clear mechanics (envelope checks, vault backup, tiered responses and structured denials) which suggests this is more than a thought experiment — it's a focused infra piece for teams that actually let agents touch production.
Big BrainNiche Gem
hammer32
114mo ago
AI/ML●●Solid
HELmR – A runtime control layer for autonomous agents
Deterministic agent governance with capability tokens beats probabilistic guardrails.
Big BrainBold Bet
systems_arch
213mo ago
AI/ML●●Solid
Hierarchical Mission Authority Architecture for autonomous systems
Authority gating for autonomous systems with reproducible safety evidence and formal assurance report.
Big BrainNiche Gem
burakoktenli
203mo ago
Security●●Solid
Grantex–Open authorization protocol for AI agents-like OAuth for agents
OAuth for agents with finalized v1.0 spec, but adoption is the real challenge.
Bold BetBig Brain
mishrasanjeev
203mo ago