Carto fixes this by giving AI agents what they are missing - Domain Map (automatic, no config), blast radius before any change, cross domain violation detection, Agents md for instant codebase context, 16+ mcp tools etc.

AI knowing what could break before it start editing code. Feels like most tools are focus on generating code faster. Maybe the next step is helping AI understand systems better.

MIT licensed , Runs entirely local , No data leaks. Tested on codebase like VScode, prisma, zed and more ( having over 10k+ files)

If you have any questions or patterns or ideas lets discuss. There is so much more things that can be done with this coz this thing i made is not just related to programming languages if you u see it u can use it to parse many more types of works.

Comments URL: https://news.ycombinator.com/item?id=48380183

Points: 1

# Comments: 1

Remote: Yes

Willing to relocate: Yes

Technologies: AWS, Python, TypeScript, FastAPI, Next.js, PostgreSQL, Terraform, Docker, Cloud Security

Resume: https://drive.google.com/file/d/19od48rlgRadrIrUGosrloe1LctC...

GitHub: https://github.com/theanshsonkar

I’m a CS student who spends most of his time building cloud infrastructure and security tools.

I have built Emfirge, A Cloud Infrastructure Reasoning platform that helps teams understand attack paths, blast radius, risky configurations, before they deploy the infra and how to fix them.

I also built Carto, an open-source tool that helps AI agents understand codebases. It maps architecture, detects domains, traces dependencies, and shows what parts of a system might be affected by a change. It's giving AI the ability to think architecturally.

I have been working on cloud infrastructure, security, developer tools, DevOps, platform engineering, and backend system from the past 2 years. Also got seleced in Accelerator program Canopy by Founders Inc.

Looking for internships, research opportunities , or full time opportunities where I can contribute to infrastructure, security, or developer tooling.