openshell 开源项目推荐（76 个）

NVIDIA /NemoClaw

借助托管推理，在 NVIDIA OpenShell 中更安全地运行 Hermes、LangChain Deep Agents 和 OpenClaw 等智能体

TheAiSingularity /hermesclaw

Hermes Agent (NousResearch) sandboxed by NVIDIA OpenShell — hardware-enforced network/filesystem/syscall policy, full memory + gateway stack

trustabl /agent-network-access-probe

Finds and fixes agent network access risks in OpenShell and Docker sandboxes.

trustabl /agent-dashboard

Agent dashboard runs reliability scans, skills, and network access probes.

NVDLI /NemoClawDLI

Free NVIDIA DLI course: build, coordinate, and secure AI agents with NemoClaw and OpenShell. Browser-based, no GPU required. Available in English, Spanish, and Brazilian Portuguese.

lensapp /openshell-k8s-operator

OpenShell Kubernetes Operator

volkgg /openfused

OpenFused is a shared memory and messaging layer for AI agents, built on plain files. It gives agents persistent context, signed mail, and peer sync without locking them into a proprietary runtime.

OpenRod /OpenRod

One-click sandboxes for AI agents, with egress policy, MCPs, skills and audit. Built on NVIDIA OpenShell.

aknochow /ogo

OGO (OpenShell Gateway Operator): Deploy and manage NVIDIA OpenShell Gateway instances on OpenShift

shaharia-lab /openshell-webui

A web console for OpenShell. Everything you do with the openshell CLI (sandboxes, policies, proposals, providers, workspaces) from your browser, without giving up its security model.

FloHofstetter /shoreguard

Open source control plane for NVIDIA OpenShell

karthikrshet /NVIDIA-Agent-Doctor

NVIDIA AI environment diagnostics, security, compatibility, and benchmarking CLI.

bradleyhodgkinson0-beep /Shellforge

Generate reverse shells and payloads for CTFs, labs, and security training with Shellforge's fast CLI and format options

Capsize-Games /headlesscode

Coding-agent harness with recursive self-improvement (RSI), parallel Git worktree workers, skills and MCP extensions, and CLI and HTTP interfaces.

prahari-ai /grdl

The YAML standard for AI agent governance. Write rules once, compile to any runtime. Deterministic. Sub-microsecond. Three templates: enterprise, DAO, AI safety. Seven governance laws.

oked-ai /oked-openshell

Action-specific human approval for agents in NVIDIA OpenShell, as a supervisor middleware

juyoungml /nemo-k-cards

Research Korean events, create English Instagram carousels, and publish with human approval. Claude Code + NVIDIA OpenShell.

LazaUK /AIFoundry-NemoClaw-AKS

Running Nvidia's NemoClaw / OpenShell in Microsoft Azure environment on Kubernetes platform.

mmporong /rl-triage-agent

Nemotron agent for diagnosing RL training failures and verifying recovery in Isaac Lab.

gajeshbhat /gauntlet

Don't read the code an AI agent wrote: make it run a gauntlet. Tests, CRAP score and mutation testing for Python, with evidence you can read. Runs locally; optional OpenShell isolation; Claude Code plugin.