OpenShell Research / Dev Notes
OpenShell Research / Dev Notes
Dev Notes
Technical notes from the OpenShell team – reproducible research, benchmarks, and use case examples.
Featured note
Latest from the team
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
Recent notes
The working archive
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