claudlos/hermes-katana
State of the art security for AI agents
This project helps ensure that AI agents behave securely and don't accidentally (or maliciously) expose sensitive information or execute harmful commands. It inspects all data flowing into and out of an AI agent, identifying and stopping potential threats like prompt injections or attempts to misuse tools. It's designed for anyone deploying or managing AI agents in a production environment who needs robust security against emerging AI-specific vulnerabilities.
Use this if you are developing or operating AI agents and need to protect them from sophisticated attacks like prompt injection, data exfiltration, or unauthorized command execution.
Not ideal if you are developing simple, offline AI scripts that don't interact with external systems or sensitive data.
Stars
18
Forks
—
Language
Python
License
MIT
Category
Last pushed
Apr 05, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/claudlos/hermes-katana"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ghostwright/phantom
An AI co-worker with its own computer. Self-evolving, persistent memory, MCP server, secure...
dograh-hq/dograh
Open Source Voice Agent Platform
gmickel/flow-next
Plan-first AI workflow plugin for Claude Code, OpenAI Codex, and Factory Droid. Zero-dep task...
joseairosa/recall
Persistent cross-session memory for Claude & AI agents. Self-host on Redis/Valkey, or use the...
lintsinghua/claude-code-book
《御舆：解码 Agent Harness》42万字拆解 AI Agent 的Harness骨架与神经 —— Claude Code 架构深度剖析，15 章从对话循环到构建你自己的 Agent...