adithyan-ak/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.
Build with Backblaze B2
SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.
Loading star history...
Where it stands
Rank, growth pace and release cadence relative to everything GStars tracks.
2 releases in the last 90 days, the latest 70 days ago, with 3 contributors on GitHub.
Use Cases & Benefits
- Provides an offensive security framework for AI agent infrastructure covering recon, credential looting, model exfiltration, poisoning, and attack-path analysis.
- Unifies multi-layer AI agent attack surfaces into a single Neo4j graph with automated pathfinding and risk scoring for comprehensive threat visibility.
- Use for red team assessments targeting AI service stacks including MCP, A2A, model gateways, and vector stores to identify attack paths and vulnerabilities.
- Use for security teams to inventory credentials, model metadata, and detect indirect prompt injections across AI infrastructure components.
- Use for researchers and developers to simulate and validate reversible offensive actions like tool poisoning and config implants in AI agent environments.
Should you depend on it?
License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.
License
Apache 2.0
Permissive: commercial use, modification and redistribution are allowed with attribution; includes an explicit patent grant from contributors.
Community files
- README: present
- Contributing guide: present
Watch-outs
No watch-outs from GStars' checks.
General guidance from repository metadata, not legal advice. How we score
From the README
MCP · A2A · model gateways · inference servers · vector stores · MLOps · notebooks · 12 agent clients
Authorized use only. AgentHound ships read-only discovery and active exploitation modules. Run it only against infrastructure you own or are written-authorized to assess. See Safety & Authorization.
AgentHound is an open-source offensive security framework for AI agent infrastructure. It runs the full engagement - recon, fingerprinting, credential looting, modelfile / system-prompt / fine-tune inventory, model inversion, tool and instruction poisoning, and config-implant persistence - across every layer of the modern agentic stack, then merges every fact into one Neo4j graph and proves the attack paths that tie it all together. Agenthound is BloodHound for the agentic stack.
Daily snapshots
Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots
Forks
84+36
Open issues
27+18
Compared with peers in AI Agents
Fastest-growing repositories GStars tracks in this cohort for the week of Nov 1, by 7-day star growth
| Repository | Stars | +7d | Health | Last release |
|---|---|---|---|---|
| vercel-labs/agent-desktop | 17.0K | +13.3K | 33 | today |
| thedotmack/claude-mem | 113.6K | +8.8K | 35 | today |
| stablyai/orca | 116.8K | +6.6K | 40 | today |
| milind-soni/OpenMausBot | 13.5K | +6.0K | 45 | today |
| HKUDS/DeepTutor | 55.5K | +5.5K | 65 | 5 days ago |
| adithyan-ak/AgentHound | 455 | — | 28 | 70 days ago |
| Category median | 55.5K | +6.6K | 40 | — |
Discover Repositories
Search across tracked repositories by name or description