Guardian
Guardian is an agent app that automates penetration testing workflows with AI for security testers authorized to test their own systems.
What it is good for
- Running security scans across a set of authorized targets
- Chaining security tools into step-by-step testing workflows
- Writing security assessment reports with evidence and severity scores
- Triaging scan findings to cut out false positives
At a glance
- Who it is for
- Setup difficulty
- Technical ยท Guided command-line setup
Level 4 of 5. You copy and paste commands into a terminal by following the instructions. Comfortable territory for vibe coders.
- Cost
- Free and open source
- Type
- Agent app
- Tasks
- Works with
- OpenAI, Anthropic Claude, Google Gemini, OpenRouter, Requesty, Ollama
Momentum
- Rank this week
- Not ranked yet
- Best rank
- None yet
- GitHub stars
- 1,945
GitHub numbers as of Nov 16, 2026. Updated weekly.
Official links
Setup steps are on the official pages. We do not repeat them here, since they change.
Questions
- Is Guardian free?
- Yes. It is free and open source.
- Do I need to know how to code to use Guardian?
- You do not need to write code, but setup means copying and pasting commands into a terminal by following its instructions.
- What does Guardian work with?
- According to its own documentation, it works with OpenAI, Anthropic Claude, Google Gemini, OpenRouter, Requesty, and Ollama.
- What is Guardian good for?
- Running security scans across a set of authorized targets, chaining security tools into step-by-step testing workflows, writing security assessment reports with evidence and severity scores, and triaging scan findings to cut out false positives.
Similar agents to Guardian
- OpenHands
OpenHands is a self-hosted control center that runs coding agents and automations on your own machine or server for developers and teams.
- OpenSRE
OpenSRE is a command-line agent that investigates failed CI builds and pushes a proposed fix for engineering teams to review.
- AgentRun
AgentRun is an agent app that cuts repeat token costs and recovers interrupted runs by letting agents learn jobs, for teams running agents.
- Codex Security
Codex Security is a command-line tool and code library that finds, checks, and fixes security vulnerabilities in code repositories for developers.
- Tracely
Tracely is a self-hostable testing tool that turns failed AI agent runs into regression tests and blocks pull requests that bring the failures back, for developers.
- ChaosIntelligence
ChaosIntelligence is a programming language that lets developers call AI agents like functions to build multi-step workflows, goal-driven bots, and live reports.