Back to browse
GitHub Repository

Quality gates for AI agents. Guards that don't get tired.

11 starsPython

We caught our AI agents self-approving their own work, so we built this

by june-jule·Mar 26, 2026·2 points·2 comments

AI Analysis

●●SolidShip ItSolve My Problem

465 passing tests, zero deps, guards extracted from 5,000+ real agent executions.

Strengths
  • Specific guard patterns like EG-06 blocking deploys without rollback plans
  • Extracted from production system with 5,000+ governed task executions documented
  • State machine enforces role separation preventing agents from self-approving work
Weaknesses
  • AI governance space getting crowded with emerging frameworks and tools
  • Guard patterns may not transfer cleanly to all agent architecture styles
Category
Target Audience

Teams deploying AI agents to production, ML engineers building agent systems

Similar To

LangGuard · Guardrails AI · LLM Guard

Post Description

465 tests, No Deps

Similar Projects

Security●●Solid

Solution for Prompt Injection of AI Agents

Execution firewall for AI agents before prompt injection causes real damage.

Big BrainBold Bet
prudhvinomos
302mo ago
Security●●●Banger

MVAR – Deterministic sink enforcement for AI agent

IFC + capabilities block prompt injection at execution sinks, not input filters—40yr research applied.

Big BrainWizardry
ShawnC21
113mo ago