Dev Notes
OpenShell's research journal – reproducible research, announcements, and implementation lessons.
Featured note
Introducing OpenShell Research
Hello, world—from the OpenShell Research team.
Read note
Recent notes
The leak is coming from inside the sandbox
A simple experiment shows why network-layer redaction isn’t enough.
Read note
What we have learned applying formal methods to control AI agents
An intro to using formal methods to reason about permission changes in long-running AI agents.
Read note
Adversarial prototype: AI policy auto-approval for long-horizon agents in OpenShell
Can an attacker agent convince an equally capable reviewer agent to grant a capability that is explicitly prohibited?
Read note
Can Formal Methods Govern AI-Generated Robot Actions?
A robotics experiment asks whether an independent, SMT-backed policy boundary can efficiently govern AI-generated plans before they reach a simulated or physical robot.
Read note
Bringing Privacy and Security to the Edge with OpenShell
Edge agents handle sensitive data and make decisions with physical consequences. Reachy Mini shows why privacy and safety controls must be deterministic and local.
Read note