AgentHound
Open-source offensive security framework for agentic infrastructure. One autonomous scan captures credentials, discovers AI services, proves concrete access, and preserves one artifact for full attack-graph analysis.
AgentHound at a Glance
- Pricing
- Free
- How you use it
- Install and run the CLI collector; optionally ingest its JSON artifact into the analysis stack.
- Who it's for
- Red-team operators testing agentic infrastructure
- Works with
- MCP A2A LiteLLM Ollama vLLM Qdrant MLflow Jupyter Open WebUI LangServe
AgentHound Key Features
- AI service discovery
- Attack graph analysis
- Credential capture
- MCP access proof
Can't Find What You're Looking For?
We build custom AI agents tailored to your specific business needs. From ideation to deployment, TinyAI.Tools is your partner in AI innovation.
No commitment required. Let's discuss your ideas.
AgentHound Alternatives
AI-Infra-Guard
A full-stack AI Red Teaming platform securing AI ecosystems via Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation. - Tencent/AI-Infra-Guard
Repello
Repello AI is the enterprise platform for autonomous AI red teaming, runtime guardrails, and continuous AI security across LLMs, AI agents, and MCP.
Guardrails AI
The AI Reliability Platform
caracal
The identity and authorization layer for AI agents. Agents never hold credentials: every action is policy-approved before it runs, delegation can only narrow, and a tamper-evident audit trail proves what happened.
agentsystems
Open-source infrastructure for AI sovereignty and governance.
Lakera
The AI-native security platform to accelerate GenAI initiatives—trusted by Fortune 500s, backed by the world’s largest AI red team.