zerodayai

Show HN: Gibson ADK and Security Runtime

Posted by zerodayai on Tuesday August 25, 2026 @11:35AM
from the show-hn dept.

https://www.zeroroot.ai

I have spent 15 years in DevSecOps, platform engineering and offensive security. Over the last year I did most of the things HN says not to do. I wrote a lot of code alone in a vacuum and built this thing far past an MVP.It started as a way to automate my bug bounty hobby and to try to find an edge so I could get more findings (scale, automation etc). I wanted agents that could run recon,...

( Read More... | 1 comment | 2 points | on HN )

Re:Comparing AI agents to cybersecurity professionals in real-world pe... on Tuesday January 06, 2026 @05:12PM (#46519585)

Im currently on the tail end of building out an agentic hacking framework; I wanted to learn the best practices of building agents (I have an SDK with memory (short/med/long), knowledgegraph/RAG, tools and plugins that makes it easy to develop new agents the orchestrator can coordinate).

I also wanted to capture what's in my head from doing bug bounties (my hobby) and 15+ years in appsec/devsecops to get it "on paper". If anyone would like to kick the tires, take a look, or tell me it's garbage feel free to email me (in my profile).

Re:Ask HN: What are you building as a side-project or side-hustle in 2... on Monday December 29, 2025 @08:44PM (#46428531)

https://github.com/zero-day-ai

I started this as a way to try to get my brain onto paper so I could be a little more systematic about bug bounties (my hobby), and utilize LLMs in a more structured manner and it morphed into this. I have a bunch of ideas for more agents (agents being a loose term), but want to get the framework baked first.

Re:Ask HN: LLM Prompt Engineering on Thursday September 18, 2025 @01:13PM (#45292268)

I am creating something along these lines, https://github.com/zero-day-ai, it's meant for security testing, but probably has most of the functionality you need (and you can write plugins fairly easily if not); you can create a prompt repository, defined by a schema that are organized my domains (again, security testing domains, but they can be expanded). If you have any features you'd like to see, or have an ideal workflow feel free to ping me: [email protected]