AI agent tools for penetration testing
Short answer: Our top pick for penetration testing: pentagi, with the highest AgentPick Score (78/100) among tools tagged "penetration-testing". Runners-up: osmedeus (72) and Agentic-Bug-Hunter (70). Compare what each does, its license and how recently it was updated below.
| # | Tool | What it does | Score | Stars | License | Updated |
|---|---|---|---|---|---|---|
| #1 | pentagi | Fully autonomous AI Agents system capable of performing complex penetration testing tasks | 78/100 | ★ 29k | MIT | 9 Oct 2026 |
| #2 | osmedeus | A Modern Orchestration Engine for Security | 72/100 | ★ 6.6k | MIT | 4 Oct 2026 |
| #3 | Agentic-Bug-Hunter | AI-powered bug bounty hunting toolkit that works with or without subscription. | 70/100 | ★ 5.3k | MIT | 9 Oct 2026 |
| #4 | xalgorix | Autonomous AI pentesting agents — real-time reconnaissance, vulnerability detection, and exploitation orchestration. Go + TypeScript. | 68/100 | ★ 1.2k | Apache-2.0 | 12 Oct 2026 |
| #5 | Pentest-Swarm-AI | Autonomous penetration testing using a swarm of AI agents. Orchestrates recon, classification, exploitation, and reporting specialists with ReAct reas… | 67/100 | ★ 3k | AGPL-3.0 | 11 Oct 2026 |
| #6 | Cybermes | Autonomous Offensive Security, Bug Bounty & Red Teaming Agent Framework powered by Hermes Agent, specialized reasoning skills, and multi-model LLM orc… | 60/100 | ★ 940 | Apache-2.0 | 2 Oct 2026 |
| #7 | Claude-BugHunter | A Claude Code skill bundle for bug hunting and external red-team work - 82 skills, 15 slash commands, 681 disclosed-report patterns curated across 24 … | 59/100 | ★ 5.1k | MIT | 14 Oct 2026 |
| #8 | AutoCVE | Agent-driven automated CVE discovery platform for source code auditing, vulnerability verification, and report generation. | 58/100 | ★ 1.2k | AGPL-3.0 | 1 Oct 2026 |
| #9 | pentest-ai-agents | Turn Claude Code into your offensive security research assistant. Specialized AI subagents for authorized penetration testing plan engagements, analyz… | 55/100 | ★ 2.3k | MIT | 6 Oct 2026 |
| #10 | pentestcode | PentestCode - Multi-agent AI penetration testing system with persistent engagement state, strategic coordination, and parallel autonomous operations. | 54/100 | ★ 845 | MIT | 2 Oct 2026 |
| #11 | AgentHound | Offensive security framework for AI agent infrastructure - recon, credential looting, model exfiltration, poisoning, and attack-path analysis across M… | 53/100 | ★ 450 | Apache-2.0 | 14 Oct 2026 |
| #12 | BugTraceAI | Open-source, self-hosted web pentesting suite with agentic scanning, analyst tools, API testing, model checkpoints and MCP integrations. | 53/100 | ★ 359 | Apache-2.0 | 14 Oct 2026 |
| #13 | T3MP3ST | autonomous red teaming platform; multi-agent offensive-security meta-harness | 52/100 | ★ 6.5k | AGPL-3.0 | 8 Sept 2026 |
| #14 | agent | Agentic offensive-security in your terminal | 50/100 | ★ 1.4k | Apache-2.0 | 31 Aug 2026 |
| #15 | cain-agent | Real-world AI penetration testing engineer for authorized assessments — built-in cloud module covering AWS/Azure/GCP + Aliyun/Tencent/Huawei clouds. B… | 49/100 | ★ 953 | Apache-2.0 | 14 Oct 2026 |
| #16 | pentestagent | PentestAgent is an AI agent framework for black-box security testing, supporting bug bounty, red-team, and penetration testing workflows. | 46/100 | ★ 3.2k | MIT | 12 Oct 2026 |
| #17 | blitzstrike | Blitz Strike — a universal MCP security-audit toolbelt. Reconnaissance at speed. Analysis in depth. Validation before report. | 45/100 | ★ 508 | MIT | 12 Oct 2026 |
| #18 | Cairn | Cairn is a general-purpose AI state-space search engine, validated first on autonomous penetration testing. Sometimes misspelled as Carin. | 44/100 | ★ 3.6k | AGPL-3.0 | 7 Sept 2026 |
| #19 | airecon | AIRecon is an autonomous cybersecurity agent that combines a self-hosted Large Language Model (Ollama) with a Kali Linux Docker sandbox and a Textual … | 41/100 | ★ 1.1k | MIT | 12 Oct 2026 |
| #20 | LitterBox | A self-hosted sandbox for red teams to test payloads against modern detection before deployment. MCP integration lets an LLM agent drive analysis end … | 33/100 | ★ 1.5k | GPL-3.0 | 5 May 2026 |
| #21 | MCP-Kali-Server | MCP configuration to connect AI agent to a Linux machine. | 22/100 | ★ 847 | MIT | 17 Mar 2026 |
| #22 | EVA | EVA is an AI-assisted penetration testing agent that enhances offensive security workflows by providing structured attack guidance, contextual analysi… | 20/100 | ★ 531 | See repo | 16 Jun 2026 |
Source: each project's public GitHub repository (description, stars, license, last push). Listed tools aren't tested or ranked by AgentPick.
How to choose
- Read the license before using it commercially.
- Check how recently it was updated and how active its issues are.
- Run it on a small, low-risk task first.
Get the best new agent tools every week. Free, with a verdict on each. Get the weekly digest
Related
AI agent tools for agent memory →
Agent building
AI agent tools for self-hosted setups →
Agent building
AI agent tools for LangChain →
Agent building
AI agent tools for sandbox →
Agent building
AI agent tools for harness engineering →
Agent building
AI agent tools for benchmark →
Agent building
AgentPick Weekly
The week's new agent tools with a verdict on each, every week. Free. We'll email you a link to confirm, and you can unsubscribe any time. See our Privacy Policy.