AgentHound
★ 452
vs
ADR
★ 2.1k
AgentHound vs ADR
AgentHound: AgentHound is an open-source offensive security framework designed to assess the security posture of AI agent infrastructure. It performs reconnaissance, fingerprinting, credential looting, and active exploitation across various layers of the agentic stack, mapping attack paths into a Neo4j graph for comprehensive analysis.; ADR: ADR (Agentic Detection and Response) is an open-source framework designed to secure AI agents utilizing the Model Context Protocol (MCP). It comprises an ADR Sensor for telemetry collection and an ADR Detector, which serves as a dual-agent benchmark and detection system.
01
TL;DR
AgentHoundSecurity & Safety · ★ 452
Performing red team engagements against AI systems.
ADRSecurity & Safety · ★ 2.1k
When to choose:
- You research detection for MCP-based agents and want to reproduce the MLSys 2026 ADR paper.
- You want a benchmark: ADR-Bench has 133 MCP servers and 303 tasks with baselines.
- You want to collect telemetry from Claude Code, Cursor and Codex into one schema with the sensor.
When to skip:
- You want a packaged product to deploy: this is research code for a paper.
- You want the ADR Explorer red-teaming engine: the README says it is not included.
- You cannot pay for Anthropic and OpenAI API calls: the default detector needs both.
02
Side-by-Side Comparison
Field
AgentHoundADRCategory
Security & Safety
Security & Safety
Stars
★ 452
★ 2.1k
License
Apache-2.0
Apache-2.0
Install Command
curl -sSfL https://raw.githubusercontent.com/adithyan-ak/agenthound/main/docker/docker-compose.public.yml | docker compose -f - -p agenthound up -d --wait && curl -sSfL https://raw.githubusercontent.com/adithyan-ak/agenthound/main/install.sh | sh
git clone https://github.com/uber/ADR && cd ADR/Detection && uv sync
Updated
2d ago
4d ago
Open Source
Yes
Yes
Tags
Offensive Security, AI Agent Security, Red Teaming
AI Agent Security, Telemetry, Detection System
03
Features
AgentHound01Full-spectrum attack surface analysis for AI agent infrastructure.
02Credential inventory and correlation across gateways and services.
03Modelfile, system-prompt, and fine-tune inventory and analysis.
04Model inversion to extract training-data residue.
05Active exploitation modules for tool/instruction poisoning and configuration implants.
ADR01ADR Sensor for collecting and normalizing agent telemetry.
02ADR Detector, a dual-agent detection system with 133 MCP servers and 303 benchmark tasks.
03Support for the Model Context Protocol (MCP) for securing AI agents.
04Provides a step-by-step workflow to reproduce benchmark detection and paper figures.
04
Use Cases
AgentHound↳Performing red team engagements against AI systems.
↳Identifying and mapping attack paths in AI agent infrastructure.
↳Assessing the security posture and blast radius of AI deployments.
↳Auditing agent configuration, prompts, and tool access for vulnerabilities.
ADR↳Securing AI agents that use the Model Context Protocol (MCP).
↳Benchmarking and evaluating the security performance of agentic AI systems.
↳Collecting and analyzing telemetry data from various AI agent platforms.
↳Red-teaming and defensive security research for agentic AI.
05
Best For
AgentHoundHidden Gem
ADRTrending
FAQ
FAQ
What is the difference between AgentHound and ADR?
Both AgentHound and ADR are in the Security & Safety category. AgentHound has 452 stars, while ADR has 2.1k stars.
Which is better, AgentHound or ADR?
The best choice depends on your use case. Choose AgentHound if Performing red team engagements against AI systems., and ADR if Securing AI agents that use the Model Context Protocol (MCP)..
Is AgentHound free or open source?
Yes, AgentHound is open source on GitHub (Apache-2.0).
Is ADR free or open source?
Yes, ADR is open source on GitHub (Apache-2.0).
Cloud Infrastructure
AdDeploy on DigitalOcean
Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.
→