swarm-ai-research/swarm

Orbit: A framework for multi-agent safety and security evaluations

OpenART is an open-source framework designed to evaluate the safety and robustness of autonomous AI agents in dynamic, long-horizon, and stateful environments. It stress-tests agent runtimes against multi-step state poisoning, privilege escalation, and tool-use vulnerabilities across 10,000+ benchmark scenarios.

Official implementation of "HarnessRisk: A Lifecycle-Oriented Benchmark for Agent Harness Safety"

The Universal Governance, Risk, Compliance (GRC) Operating System with Integrated Security for Agentic AI, Non-Human Identities, and Swarm Governance. AI SAFE² + AI Sovereignty Maturity Model (AISM), NEXUS-A2A Protocol, FORGE-Act (e.g. Marshal Plan for AI) [Dual License: MIT + CC-BY-SA]

ControlArena is a collection of settings, model organisms and protocols - for running control experiments.

[NeurIPS 2025] Official repository of RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents

[ICML 2026] AutoControl Arena: Frontier AI Risk Auto-Discovery Platform

StepShield: When, Not Whether to Intervene on Rogue Agents — NeurIPS 2026 benchmark for temporal evaluation of AI agent guardrails (9,429 trajectories, step-level annotations)

A Diagnostic Guardrail Framework for AI Agent Safety and Security