Trajeckt, a Firewall for AI Agents

Hi all, As there are more and more agents in the internet; Security is going to be a big problem. Currently, the problem is solved using a LLM to guard Agent but this creates the problem of hallucination and latency, so I coded a firewall in rust that runs under five milliseconds. This works by creating a plan and enforcing the plan; While the agent is running, we track the trajectory using graph of the tools and the actions it used and data it accessed. for per action call, this enforces using the Model context protocols list and for sequence it tracks every single tool call and data flow; there is also a taint mechanism where if the agent reads something outside of the user context, it flags and adds more security mechanism. It works by using a DAG.