# heisty-agents

- **Event:** [Gemini 4 Argon SF Hackathon](https://cerebralvalley.ai/e/gemini-4-argon-sf)
- **When:** Sun, Oct 25 at 9:00 AM – 10:00 PM (PDT)
- **Where:** San Francisco, CA
- **Team:** [Chong Yi Chin](https://cerebralvalley.ai/u/leochin17)
- **GitHub:** https://github.com/cyberleo17-VGS/argon-hack-project-heist
- **Demo video:** https://youtu.be/FCadJ9RgPGk
- **Gallery:** https://cerebralvalley.ai/e/gemini-4-argon-sf/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/gemini-4-argon-sf/hackathon/gallery/86

A security agent that make sure everything running on behalf of the coding agent owner is safe and secure.

The security agent uses a defense in depth approach powered by Gemini Argon 4

Tier 1 Tree sitter Abstract Syntax Tree:
its the foundation of using parsing to check against bash or CLI commands thats ran by the model

Tier 2: Argon 4 as a judge:
Anything that passes tier 2 gets filtered by Argon 4 using LLM as a judge approach. If it does not pass through tier 2 

Tier 3: Escalates to the human (Human in the loop
it sends a webhook to slack channel with the LLM analysis and attack path that alerts the human.

## More from Gemini 4 Argon SF Hackathon

- [turntable](https://cerebralvalley.ai/e/gemini-4-argon-sf/hackathon/gallery/83)
- [KRONOS](https://cerebralvalley.ai/e/gemini-4-argon-sf/hackathon/gallery/84)
- [SimRoboHome](https://cerebralvalley.ai/e/gemini-4-argon-sf/hackathon/gallery/85)
- [Abhi](https://cerebralvalley.ai/e/gemini-4-argon-sf/hackathon/gallery/87)
- [RoBoCo](https://cerebralvalley.ai/e/gemini-4-argon-sf/hackathon/gallery/88)
- [Listing2Living](https://cerebralvalley.ai/e/gemini-4-argon-sf/hackathon/gallery/89)

---

Markdown version of https://cerebralvalley.ai/e/gemini-4-argon-sf/hackathon/gallery/86. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt