AI/ML●Mid
Signal Core – governance, approvals, and audit receipts for agent tools
Agent governance is a real need, but closed-source binaries prevent code evaluation.
Bold Bet
d-milliken
212mo ago
Back to browse
GitHub Repository
Roles, segregation of duties, and tamper-evident audit for the AI agents you already run. Open-source, self-hosted.
0 starsTypeScript
Stop your AI agents from approving their own work
by smashini·Jun 17, 2026·2 points·1 comment
AI Analysis
●●●BangerBig BrainZero to OneSolve My Problem
Hash-chained audit logs with Ed25519 signing make agent actions verifiable offline.
Strengths
- •Deny-by-default skill grants pinned to exact versions prevent unauthorized actions
- •Segregation of duties enforcement blocks agents from approving their own work
- •Works with existing agent frameworks via proxy session or flow mode
Weaknesses
- •Requires agent framework integration — not completely transparent to existing setups
- •Self-hosted means you're responsible for infrastructure and maintenance
Category
Target Audience
Teams deploying AI agents that take real-world actions
Similar To
Oso · OpenPolicyAgent · HashiCorp Boundary
Similar Projects
AI/ML●●Solid
We caught our AI agents self-approving their own work, so we built this
465 passing tests, zero deps, guards extracted from 5,000+ real agent executions.
Ship ItSolve My Problem
june-jule
222mo ago
Developer Tools●Mid
MemLineage: governed writes for AI agents
PR-like review for agent writes, but OpenClaw adoption is niche and early.
Niche GemShip It
celastin
113mo ago
AI/ML●●●Banger
Arden – Runtime policy enforcement and governance for AI agents
Intercepts tool calls before execution to block dangerous actions like DB deletes.
Solve My ProblemBold Bet
rishabtandon
851mo ago
Developer Tools●●●Banger
Memrail – PR-style governance for AI agent writes (OpenClaw)
PR-model for agent writes solves real OpenClaw quality drift without enterprise middleware.
Solve My ProblemWizardryNiche Gem
celastin
113mo ago
AI/ML●●Solid
I Made OpenClaw Employable
Budget gates and DLP checks prevent agents from draining accounts or leaking data.
Big BrainSolve My Problem
smashini
2118h ago