AgentHound
Offensive security framework for AI agent infrastructure - recon, credential looting, model exfiltration, poisoning, and attack-path analysis across MCP, A2A, gateways, and AI services. BloodHound for the agentic stack.
| Category | AI Agent Frameworks |
|---|---|
| Author | adithyan-ak |
| Stars | 451 |
| Language | Go |
| License | Apache-2.0 |
| Last update | 2026-10-14 |
| Source | https://github.com/adithyan-ak/AgentHound |
Tags: a2a, agentic-ai, ai-agents, ai-security, attack-paths, bloodhound, llm-security, mcp, model-context-protocol, neo4j, offensive-security, pentesting, red-team, security-tools
Maintain this project? Get it featured.
Alternatives to AgentHound
rea morluto · ★278898 · TypeScript
Reverse engineer anything with agents, from app behavior down to native binaries.
ponytail DietrichGebert · ★164692 · JavaScript
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
gemini-cli google-gemini · ★107398 · TypeScript
An open-source AI agent that brings the power of Gemini directly into your terminal.
paperclip paperclipai · ★102899 · TypeScript
The open-source app everyone uses to manage agents at work
orca stablyai · ★93851 · TypeScript
Orca is the ADE for working with a fleet of parallel agents. Run any coding agent with your own subscription. Available on desktop, mobile and remote runtime.