AI Security Matrix

A curated list of AI-enabled security testing tools.

mayank-dev-15/AI-Pentest-Agent

Licence
MITREADME says Apache-2.0
Maintainers
1 contributor · top author wrote 100%
Size
5,282 lines · 26 code files · tests, CI
Bundled tools
none found
Shares files with
no overlap found
README says MIT
The project contradicts its own files

Before running it

Your right to use, modify or redistribute it is unclear yes
The install script is fetched when you run it, so what runs is not the version anyone reviewed no
It sends data to a third party that is not the model provider no
Part of what ships cannot be reviewed by reading the source no
Its container is given access back to the host, so the boundary does not hold no

agent

Last updatedCategoryToolScopeStarsFlags
★ today agent h5i-dev/h5i new
Gives an agent a browser that controls its own network traffic, so the model can capture, edit, replay and compare the requests a web app sends without a proxy in between. Each session runs under a network policy and records every fetch it allowed or refused.
 webappapirecon 797 remote
★ 1d agent google/mantis new
Reads a codebase and its commit history, builds a threat model from them, and sends agents to chase each hypothesis it raises. It then tries to reproduce each finding in a sandbox and attacks its own patch to check the fix holds, working from source alone with no running target.
 code 2.5k none
★ 6d agent KeygraphHQ/shannon new
Reads an application's source to pick its attack paths, then attacks the running web app and its API through a browser and command-line tools. A finding reaches the report only after it has been exploited.
 webappapicode 49k none
★ 23d agent blacklanternsecurity/red-run new
An orchestrator inside Claude Code that runs a team of agents across an internal network and Active Directory engagement. It lays out the paths open to you and you pick one, or it works through them on its own, keeping the engagement's state in one place.
 networkadwebapprecon 291 none
★ today agent usestrix/strix
Drives a live pentest against a running web app or API, choosing each probe from what the last one returned, then reports what it found.
 webappapicoderecon 70k remotecallout
★ today agent berylliumsec/nebula
A desktop workspace holding the terminal, notes, findings and report in one place, with an approval pause between what the model proposes and what actually runs.
 networkrecon 1.1k callout
★ today agent dreadnode/ares
Puts red and blue agents on the same live infrastructure at once: one side chains Active Directory attacks, the other reads the logs and writes detections back to the dashboard. A single Rust binary.
 adnetworkredteam 99 none
★ 1d agent PurpleAILAB/Decepticon
Runs a red-team engagement from a terminal CLI, with an orchestrator that starts specialist stacks like BloodHound or a C2 server only when the engagement reaches them.
 redteamnetworkwebapp 6.4k remotecalloutescape
★ 1d agent xalgorix/xalgorix
Runs a second, independent agent whose only job is to re-exploit what the first one claimed, so a finding is either reproduced or dropped. One self-hosted binary with a local dashboard.
 reconwebappnetwork 1.2k remotecalloutescape
★ 1d agent MythicAgents/Sage
Installs into a Mythic C2 server and operates it from the inside, reasoning over the live callbacks and the BloodHound graph to issue Mythic tasks. It never touches the target itself.
 redteamad 30 none
★ 2d agent Armur-Ai/Pentest-Swarm-AI
Runs many agents against one scope at once, coordinating through a shared board so a new finding immediately wakes whichever agent it matters to. Written in Go.
 webappnetworkrecon 3.0k remote
★ 2d agent samugit83/redamon
Chains recon, exploitation and post-exploitation, then carries a finding further than a report: it writes the fix and opens a pull request on your repository.
 redteamadnetworkrecon 3.2k remotecalloutescape
★ 2d agent AIPentest/CyberStrikeAI
Keeps an operation replayable: the plan, the approvals, the evidence and the attack-chain model live in one workspace you can re-run afterwards. Built in Go, with its tools served over MCP.
 networkwebapp 7.9k none
★ 4d agent vxcontrol/pentagi
Runs autonomous pentest agents from a self-hosted web console, each inside its own Docker container rather than on the host. You start a task in the browser and watch the agents work it.
 webappnetworkrecon 32k escape
★ 4d agent capture0x/AdStrike
A menu-driven Active Directory framework that carries credentials and Kerberos state in one session across its modules. It also serves those modules over MCP, so an editor's model can drive them instead.
 ad 386 licence
★ 9d agent GH05TCREW/pentestagent
A terminal UI for black-box testing that hands the model a real browser alongside the usual command tools, so it can work an application the way a user would.
 webappapi 3.2k escape
★ 12d agent 0xSteph/pentest-ai
Drives the investigation from an AI client you already use, over MCP, and hands each claimed exploit to an oracle that has to reproduce it. What survives ships as a capsule you can replay yourself.
 webappnetworkrecon 1.8k none
★ 20d agent ipa-lab/hackingBuddyGPT
A framework for building your own testing agent rather than a finished one. It supplies the model plumbing, the target connectors and the run limits, and you write the use-case in a few dozen lines.
 network 1.3k none
32d agent cettocdx/rift
Takes a target and an objective in plain language, then plans and runs the whole job inside a sandbox. A second mode answers questions about a finding without acting on it.
 webappnetwork 11 remotecallout
68d agent bugbasesecurity/pentest-copilot
Connects to a Kali box you already run and works it from the browser, issuing the commands there and reading the output back.
 webapprecon 1.5k escape
69d agent Nightlysec/nightly
Runs inside CI on a pull request and blocks the merge when it can validate a bug, rather than being driven from a terminal against a live target.
 webappapicoderecon 1 remote
80d agent NeoTheCapt/RedteamAgent
Turns a coding CLI you already use into a five-phase lab workflow with eight specialist subagents, running every tool in Docker and keeping the run resumable.
 webappredteam 153 licence
99d agent GreyDGL/PentestGPT
Works a target in named stages, feeding each stage's findings to the next, and drives Claude Code or Codex to do the actual running. Built for CTF categories as much as for engagements.
 webappnetworkrecon 16k remote
120d agent mayank-dev-15/AI-Pentest-Agent
Ships its own port scanner and web recon rather than wrapping the usual tools, and the model only plans the attack chain. Without a key it falls back to a fixed planner.
 webapprecon 3 licence
archived agent aliasrobotics/cai
The reference framework behind a body of published AI offensive-security research, kept as its final source tree. Its capabilities moved on to a commercial successor.
 networkwebapprecon 9.8k remoteescape
193d agent chetstriker/LLMtary
A Flutter desktop application that can run the whole engagement against a model on your own GPU, feeding each phase's findings into the next phase's prompt.
 reconwebapp 42 remote