AI Safety

Operation-bound protection for autonomous AI agents: contain and verify operations before committing changes, understand intent and risk across long-running work, and detect threats across agent and system activity.

不死鸟 Phoenix — Hermes Agent 插件：路由分档/风险防线/自愈/存档点提醒/审批策略自适应，官方钩子接入，不改 Hermes 核心代码

The action firewall for AI agents. Enforce policy and human approval before risky tool calls, shell commands, workflows, and production changes, with auditable evidence.

A Geiger counter for AI agents — one read-only command that inventories every agent, MCP server, plugin, and AI extension on a machine

Delta MCP is a free app that sits between your AI apps and their MCP servers: any server, every tool. It checks each task before it runs, applies it all or nothing, reads back what it changed and lets you undo it. Far fewer tokens on multi-step tasks, and shortcuts that run on a schedule. Coming soon for macOS, Windows and Linux.

Subagent Verification for Claude AI Code Networks 2026

Agent orchestration & security template featuring MCP tool building, agent2agent workflows, mechanistic interpretability on sleeper agents, and agent integration via CLI wrappers

🛡️AutoControl Arena: Synthesizing Executable Test Environments for Frontier AI Risk Evaluation

Measuring how well CLI agents like Claude Code or Codex CLI can post-train base LLMs on a single H100 GPU in 10 hours

Runtime defense against memory poisoning in AI agents (OWASP ASI06). Drop-in for LangChain, OpenAI Agents, AutoGen, CrewAI and mem0.

A pre-execution guard for AI coding agents. It blocks destructive Git and file system commands, plus common attempts to access sensitive files, before a tool call runs. Supports Amp Code, Antigravity CLI, Claude Code, Codex, Cursor, DeepSeek Harness, Devin CLI, GitHub Copilot CLI, Grok Build, Hermes Agent, Kimi Code, OpenClaw, OpenCode, and Pi.

🦀 Prevents outdated Rust code suggestions from AI assistants. This MCP server fetches current crate docs, uses embeddings/LLMs, and provides accurate context via a tool call.

Open-source governance and hard gates for AI coding agents across Claude Code, Codex CLI, and Pi.

AI 应用合规网关 · 一行命令体检 AI 项目的「数据出境 / 硬编码密钥 / 个人信息暴露」（网安法·PIPL·等保2.0·数据出境·AI标识），并给出境内模型替代建议；可作运行时防护拦截注入与数据外泄 · 中文优先 · 零依赖 · 开源

Access control for AI agents. Set what Claude Code, Codex, Gemini, Cursor and any MCP server are allowed to do, review risky actions before they run, and keep every action on the record.

Practices, protocols, and skills for AI-driven software development. Skills and safety hooks for Claude Code, Codex, OpenCode, Cursor, Antigravity, and any agent supporting the Agent Skills standard.

full guide to help you integrate AI in your workflow, for both beginners and experienced users

One config to rule all your AI agents: portable (every project, every session), effective (curated writing, routing, skills), and safer (destructive-command guard).

Universal AI Charter: plain-language governance principles and a public certification registry for AI models, built on disclosure instead of a development slowdown.

👾 下一代透明智能体架构 | Next-Gen Transparent Agent Architecture 🔍 全行为审计 | 🛡️ 两段式安全调用 | 🧠 双水位记忆 | ⏰ 心跳任务 📊 P0 级事故率降低 80% | 兼容 OpenClaw + Claude Code 技能生态

Anti-hallucination research mode for Claude Code. Toggle on/off to enforce citation requirements and source grounding.

Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default, fully auditable from the session log (approval/asked -> autoReview/verdict -> approval/decided).

A discipline layer for Claude Code. Hooks at every tool boundary, a workflow that runs from intake to commit, and a small constitution the agent cannot bypass.

Tamper-evident tracing, policy gates and cross-checks for AI agents: see what the agent did, and why.