capability
Agent Safety agents
This page lists every AI agent in the MeshKore directory tagged with the Agent Safety capability. Agents are sourced from public platforms (GitHub, Hugging Face, npm, PyPI, awesome-list curations, and direct submissions), normalized by the MeshKore worker, and ranked by GitHub stars. Each card links to the agent's profile with details on capabilities, framework, language, freshness, and source attribution.
22 agents in this capability · ranked by popularity
Top 22 Agent Safety agents
Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses | 500+ Papers | Perception, Cognition…
Your AI agent just burned $200. AgentGuard stops it at $5. Runtime cost guardrails for AI agents — budget…
Atbash safety guard for LangChain DynamicStructuredTool
TypeScript SDK for Ovrule case-file classification, guardrails, and receipt verification.
Atbash safety guard for LangChain DynamicStructuredTool
Atbash safety guard and audit nodes for LangGraph workflows
Atbash safety judge plugin for AutoGen-style multi-agent orchestration
Atbash safety judge plugin for AutoGen-style multi-agent orchestration
Guardian T-Rex for your multi-agent repo. Isolated worktrees, file locks, and PR-only merges stop parallel…
Atbash safety guard and audit nodes for LangGraph workflows
A type-checker for AI tool calls — strict argument validation, ghost-argument stripping, and self-healing…
Formal behavioral specification and runtime enforcement for autonomous AI agents. Agent Behavioral Contracts…
Runtime security guardrails for AI agents — inspect, control, and audit every tool call. Zero-dependency…
Runtime security guardrails for AI agents — inspect, control, and audit every tool call. Zero-dependency…
Deterministic policy runtime for AI agents. Same policy file gates CI and enforces in production, with no LLM…
TypeScript reference implementation of the guardian-agent spec: a runtime supervisor for tool-using LLM…
Atbash safety judge exposed as a standalone MCP server
Atbash safety judge exposed as a standalone MCP server
AgentAssert Type-C kernel — formal behavioral contracts for AI agent harnesses. Provider-blind…
Agentic AI audits for tool-use, memory, permissions, and prompt injection
Framework instalavel para agentes de IA que reduz contexto, roteia risco, valida entregas e registra…
EMILIA Protocol guard for LangChain tools: a named human approves the exact irreversible action (Face ID /…