by antgroup · Codex Skill · ★ 171
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
AgentAegis English | 简体中文 AgentAegis builds a multi-dimensional, defense-in-depth runtime security architecture for OpenClaw-style agents, implementing five-layer defense across the full lifecycle of LLM agents in various Claw environments — from initialization to execution — covering security and reliability risks in agent execution services, including skill poisoning, memory contamination, intent misalignment, malicious execution, and resource exhaustion. As a lightweight built-in security plugin, AgentAegis proactively triggers defense mechanisms at critical OpenClaw stages to dynamically safeguard agent runtime security. It also provides configurable risk identification and response policies for security operators to flexibly and extensibly address agent runtime threats, as well as sensitive file and skill asset protection for everyday users to safeguard personal privacy and assets. 💫 Architecture AgentAegis builds a multi-dimensional, defense-in-depth architecture for OpenClaw, forming a complete security closed loop across the full lifecycle from initialization to execution.
| Stars | 171 |
| Forks | 23 |
| Language | TypeScript |
| Category | Codex Skill |
| License | Apache-2.0 |
| Quality Score | 68.3510284318435/100 |
| Open Issues | 5 |
| Last Updated | 2026-06-26 |
| Created | 2026-03-31 |
| Platforms | node |
| Est. Tokens | ~18k |
These tools work well together with agent-aegis for enhanced workflows:
Looking for a agent-aegis alternative? If you're comparing agent-aegis with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
🚀 JoySafeter: An enterprise AI Agent Platform—Not just chatting. building、running、testing, and tracing autono
A selective learning and memory substrate for agentic systems — typed, revisable, decayable memory with compet
Open-source firewall for AI agents. Policy engine that audits and controls what OpenClaw, Claude Code, Cursor,
OpenClaw-inspired autonomous AI agent built entirely in n8n. Adaptive RAG-powered memory, Skills via MCP templ
The missing linter and lsp for AI coding assistants. Validate CLAUDE.md, AGENTS.md, SKILL.md, hooks, MCP. Plug
Security toolkit for AI agents. Scan your machine for dangerous skills and MCP configs, monitor for supply cha
Explore other popular codex skill tools:
agent-aegis is AgentAegis is a lightweight plugin providing full-lifecycle runtime protection for OpenClaw.. It is categorized as a Codex Skill with 171 GitHub stars.
agent-aegis is primarily written in TypeScript. It covers topics such as agent, agent-security, llm.
You can find installation instructions and usage details in the agent-aegis GitHub repository at github.com/antgroup/agent-aegis. The project has 171 stars and 23 forks, indicating an active community.
agent-aegis is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to agent-aegis on Agent Skills Hub include JoySafeter, membrane, rampart. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.