Pinned Loading

1. agentsec-ecosystem/ai-loopguard agentsec-ecosystem/ai-loopguard Public archive

   Circuit breaker and escalation for LLM agent loops. Detects stuck patterns — repeated errors, test failures, hallucination cycles — and escalates to a stronger model. Drop-in for LangGraph, CrewAI,…

   Python 1

2. ai-tierforge ai-tierforge Public

   Multi-model LLM tier router with cost-per-completed-task accounting. Route to the right model. Track the real cost.

   Python 2

3. agentsec-ecosystem/agent-tooltrust agentsec-ecosystem/agent-tooltrust Public archive

   Contextual risk and permission engine for tool-using AI agents — allow, audit, escalate, or deny with explainable policy

   Python 7

4. planner-critic-engine planner-critic-engine Public

   Hierarchical task planning with an LLM critic — a planner decomposes a goal into a typed plan, a critic audits each subtask for feasibility, risk, missing steps, unsafe sequencing, and weak rollbac…

   Python 2