NVIDIA/OpenShell

OpenShell is the safe, private runtime for autonomous AI agents.

5 skills listed · Apache 2.0 · 20.9k stars · last pushed 31 Oct 2026

NVIDIA/OpenShell on GitHub

Across these 5 skills

Pattern check

Nothing flagged in 5

What it can touch

1 touches credentials
5 name web addresses
3 run shell commands
+1 more
- 3 reach the network

Checked at commit 42671c2 on 1 Nov 2026. 1 skill isn't listed while QAI reviews a check result.

Skills

Skills in NVIDIA/OpenShell
Skill	What it can touch	Pattern check	Licence	Updated
debug-inferenceDebug inference clients that use an attached provider and its native endpoint, including hosted APIs and host-local Ollama, vLLM, SGLang, TRT-LLM, LM Studio, or NIM. Use for provider attachment, endpoint policy, credential substitution, topology, and migration from the removed managed inference endpoint. Trigger keywords - debug inference, managed inference endpoint, local inference, ollama, lm studio, vllm, sglang, trtllm, NIM, inference failing, model server unreachable, credential_endpoint_mismatch, host.openshell.internal. Runs shell commands +1 more Pattern check: Nothing flaggedApache 2.0Updated 25 Sept 2026	Runs shell commands Names web addresses	Pattern check: Nothing flagged	Apache 2.0	25 Sept 2026
gator-gateValidate and monitor OpenShell GitHub issues and PRs using the gator:* state machine. Use when asked to triage issues/PRs for project validity, gate PRs, run gator, validate submissions, or monitor PRs toward merge readiness. Runs shell commands +2 more Pattern check: Nothing flaggedApache 2.0Updated 12 Oct 2026	Runs shell commands Reaches the network +1 more	Pattern check: Nothing flagged	Apache 2.0	12 Oct 2026
generate-sandbox-policyGenerate sandbox security policies from plain-language requirements and optional REST API documentation. Produces L4 or fine-grained L7 network policies and ordered network middleware configuration. Use for API access rules, middleware host selection, failure behavior, or built-in and operator-run middleware attachment. Trigger keywords - generate policy, create policy, update policy, change policy, sandbox policy, network policy, API policy, security policy, allow API, restrict API, network middleware, supervisor middleware. Reaches the network +1 more Pattern check: Nothing flaggedApache 2.0Updated 26 Oct 2026	Reaches the network Names web addresses	Pattern check: Nothing flagged	Apache 2.0	26 Oct 2026
openshell-cliGuide agents through using the OpenShell CLI (openshell) for sandbox management, gateway registration, provider configuration and refresh, profile management, policy iteration, settings, service exposure, BYOC workflows, and attached-provider inference. Covers basic through advanced multi-step workflows. Trigger keywords - openshell, sandbox create, sandbox exec, sandbox connect, logs, provider create, profile list, profile describe, provider refresh, policy set, policy get, settings, service expose, forward, port forward, BYOC, bring your own container, inference, use openshell, run openshell, CLI usage, manage sandbox, manage provider, gateway add, gateway select. Touches credentials +3 more Pattern check: Nothing flaggedApache 2.0Updated 30 Oct 2026	Touches credentials Runs shell commands +2 more	Pattern check: Nothing flagged	Apache 2.0	30 Oct 2026
openshell-policy-advisorUse when an OpenShell sandbox returns policy_denied, mentions policy.local, or needs a narrow network policy proposal. Names web addresses Pattern check: Nothing flaggedApache 2.0Updated 15 Jun 2026	Names web addresses	Pattern check: Nothing flagged	Apache 2.0	15 Jun 2026

Not listed from this repo

23 project-internal skills.