agent-aegis

About agent-aegis

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.

Quick Facts

Compatible Skills

These tools work well together with agent-aegis for enhanced workflows:

• shellward — semantic(0.24)+complementary+rare_topics+same_lang+similar_pop (53%)
• siclaw — semantic(0.18)+complementary+same_lang+similar_pop+shared_platform (51%)
• tweetclaw — semantic(0.19)+complementary+rare_topics+same_lang+similar_pop (51%)
• lobu — semantic(0.18)+complementary+same_lang+similar_pop+shared_platform (51%)
• hivemind — semantic(0.17)+complementary+same_lang+similar_pop+shared_platform (51%)

More Codex Skill Tools

Explore other popular codex skill tools:

• openclaw ⭐ 392.5k
• hermes-agent ⭐ 255.2k
• ui-ux-pro-max-skill ⭐ 136.1k
• agent-skills ⭐ 106.3k
• open-design ⭐ 102.0k
• taste-skill ⭐ 99.1k
• orca ⭐ 98.1k
• graphify ⭐ 76.9k
• career-ops ⭐ 75.7k
• system_prompts_leaks ⭐ 69.9k

Popular TypeScript Agent Tools

• openclaw ⭐ 392.5k · Codex Skill
• rea ⭐ 335.5k · MCP Server
• n8n ⭐ 208.0k · MCP Server
• claude-code ⭐ 151.8k · Agent Tool
• gemini-cli ⭐ 107.5k · MCP Server

Frequently Asked Questions