A personal AI agent where the LLM is structurally incapable of executing anything. Every action is proposed, evaluated, and executed by separate processes. A fully compromised agent cannot cause harm.

This container has also been tested and will work on both x64 and ARM64 based CPU architecture. This repository includes an example compose.yaml file you can use to set up your server. All files you ...

More than a dozen malicious packages have been discovered on the npm package repository since the start of August 2023 with capabilities to deploy an open-source information stealer called Luna Token ...