by antgroup · Codex Skill · ★ 171
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.
| 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:
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.