jsaiOS
An agent runtime where every tool has a risk level. Read-only tools run, changes need approval at the terminal, and high-risk tools are never offered to the model. Every request is audited.
How it works →c3rb3rus · security-first AI
c3rb3rus builds security-first AI that runs on local hardware. The first piece, jsaiOS, gives a model a short list of tools and a risk policy that decides what it may do, what needs a human yes, and what it can never touch.
Small, testable pieces that grow into one platform. Each one is built to be attacked, by me first.
An agent runtime where every tool has a risk level. Read-only tools run, changes need approval at the terminal, and high-risk tools are never offered to the model. Every request is audited.
How it works →A certification quiz partner that runs on local models. One model writes questions, a second model checks every answer key, and review is adaptive and spaced.
How it works →Full-disk encryption with remote unlock, custom Secure Boot keys, hardware security keys, and local models served LAN-only behind API keys. Writeups will cover what broke and how it was fixed.
Writeups →A model gets the narrowest tool that does the job, never a shell.
Tool calls are validated against a schema before a human is even asked.
Prompts, keys and data stay on hardware I control.
Every decision is logged. Argument values never are.