Skip to content

docs(research): assess NVIDIA's agent safety platform, OpenShell and OpenWorker - #246

Closed
praxagent wants to merge 3 commits into
mainfrom
docs/nvidia-agent-safety
Closed

praxagent wants to merge 3 commits into
mainfrom
docs/nvidia-agent-safety

Conversation

@praxagent

@praxagent praxagent commented Sep 30, 2026 •

Copy link
Copy Markdown
Owner

Three assessments, credited to their authors.

NVIDIA Open Agent Safety Platform + OpenShell (nvidia-open-agent-safety-platform.md). Confirms the Muse-parity containment. Adopt:

  • an out-of-band wire record in the secrets proxy, checked against Prax's own trace;
  • a newly-granted-access diff plus a ceiling for every egress-policy change;
  • a time-boxed evaluation of OpenShell as prax-sandbox's runtime. It has per-program network policy and a policy prover, which we lack, but it's 0.1.x.

The DPU hardware is out of reach.

OpenWorker (Andrew Ng et al., MIT; openworker.md). The closest peer to Prax's governance stance. Adopt:

  • hard floors enforced after every risk-lowering rule. A real gap today: earned_trust.py can lower browser_request_login / browser_finish_login from HIGH to MEDIUM on self-reported success.
  • parked approvals for unattended runs, instead of refusing and losing the work.
  • approval provenance on every audit entry.

All queued in the adopt tracker's Containment section. Docs only; doc tests pass.

Document + adopt two ideas; confirmation of the Muse-parity containment.
- An out-of-band wire record in the secrets proxy — the tool calls the model
  returned, hashed, append-only, where Prax can't write — checked against
  Prax's own trace, so a compromised Prax can't hide activity by editing it.
- A diff of newly granted access for egress-policy changes and timed grants.
The DPU hardware is out of reach; OpenShell (0.1.x) is a peer to watch.
OpenWorker (Andrew Ng et al., MIT): the closest peer to Prax's governance
stance. Adopt hard floors — a declared set enforced after every rule that can
lower risk; Prax's earned trust can lower two login steps from HIGH to MEDIUM
on self-reported success today — and parked approvals for unattended runs
instead of refusing and losing the work. Plus approval provenance per call.

OpenShell's product page adds per-program network policy and a policy prover
with an access ceiling: queue the ceiling, and a time-boxed evaluation of
OpenShell as prax-sandbox's runtime.
Not ruled out: Prax should be highly competitive with OpenShell. Candidate
routes recorded — per-program proxy identity inside the sandbox, cgroup/eBPF
attribution, or OpenShell's supervisor after the evaluation.
@praxagent

Copy link
Copy Markdown
Owner Author

Folded into #256, which contains every commit from this branch (the five research PRs were a stack, and stacked PRs re-conflict after every squash merge). Merge #256.

@praxagent praxagent closed this Oct 2, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant