AI agent
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.
- Rank
- #530 of 2,793
- Stars
- 125★ +51/wk
- On radar
- since 2026-07-30
Momentum
rate of rise, not size · recomputes hourly
54.8
24h· new7d· new
Collecting daily history; the trend chart appears after 3 days on the radar
Why it's ranked
AgentHound is an AI agent ranked #530 of 2,793 on the Cresting momentum radar, with a score of 54.8. It has 125 GitHub stars, +51 in the last 7 days, and has been tracked since 2026-07-30.
Every score decomposes into published factors, the same math for every tool, paid or not. Read the methodology →
| Velocity (weighted, cohort-normalized) | 0.924 |
| Recency boost | 0.000 |
| Signal decay | 0.990 |
| Corroboration | 1.000 |
| Quality gate | 1.000 |
Raw signals (30 days)
github · forks+13 in window · 29 latest · 2 snapshots
github · stars+51 in window · 125 latest · 2 snapshots
Related ai agents
- qwen-audio-agentA realtime voice runtime that keeps Agents talking, working, and present. Real-time Voice Runtime for AI Agents#1 · 484★
- deer-workflowAn open-source Dynamic Workflow runtime that keeps orchestration in TypeScript and delegates semantic work to replaceable Agent runtimes.#4 · 359★
- openclaude-improvedruns anywhere. uses anything#5 · 562★
- cindyConsider it done. The open-source AI agent that works out of the box · 想到，就能做到。开源、开箱即用的 AI Agent。#6 · 1,190★
- numbatVisibility into AI agent activity on endpoints, with on-device detection, optional pre-action blocking, and forensic reconstruction.#7 · 430★