{"slug": "red-hat-openshell-podman-fedora-rhel-vertex-ai-anthropic-quickstart", "title": "Red Hat: OpenShell + Podman + Fedora/RHEL  Vertex AI Anthropic Quickstart", "summary": "Red Hat has released a new integration enabling developers to run Anthropic's Claude Code and OpenCode AI coding assistants locally using OpenShell, Podman, and Fedora or RHEL systems with Vertex AI backend support. The setup allows users to create a local sandbox environment that connects to Google's Vertex AI for inference, bypassing the need for direct Anthropic API keys. Developers can install the necessary packages via COPR, configure the OpenShell gateway, and launch the AI assistants with environment variables pointing to the local inference endpoint.", "body_md": "```\n# install\n$ sudo dnf copr enable maxamillion/nvidia-openshell\n$ sudo dnf install openshell-gateway openshell\n\n# start the rootless user systemd service unit\n$ systemctl --user start openshell-gateway.service\n\n# add the local openshell gateway to your client config\n$ openshell gateway add https://localhost:17670 --local\n\n# Follow the Vertex AI Claude Code instructions to setup your gcloud creds\n# https://docs.google.com/document/d/1eNARy9CI28o09E7Foq01e5WD5MvEj3LSBnXqFcprxjo/edit?tab=t.0#heading=h.8ldy5by9bpo8\n# MAKE SURE TO GET YOUR PROJECT NAME, YOU'LL NEED IT IN THE FOLLOWING EXPORT\n\n$ export vertex_project=\"MY_ORGS_GCLOUD_PROJECT\"\n\n# Enable the providers v2 feature flag\n# (this is necessary for now, but will go away when we migrate from v1 to v2 upstream)\n$ openshell settings set --global --key providers_v2_enabled --value true --yes\n\n# Create the provider credential in OpenShell\n$ openshell provider create --name vertex-local --type google-vertex-ai --from-gcloud-adc --config VERTEX_AI_PROJECT_ID=\"${vertex_project}\" --config VERTEX_AI_REGION=global\n\n# Set the inference provider\n# NOTE: the model is ignored by claude code, but openshell requires the setting\n$ openshell inference set --provider vertex-local --model claude-sonnet-4-6\n\n# Create a sandbox using this provider credential\n$ openshell sandbox create --name my-sandbox --provider vertex-local\n\n# Once inside the sandbox, either run Claude Code or OpenCode as follows:\n\n# Claude Code\n$ ANTHROPIC_BASE_URL=\"https://inference.local\" ANTHROPIC_API_KEY=unused claude --bare\n\n# OpenCode\n$ ANTHROPIC_BASE_URL=\"https://inference.local/v1\" ANTHROPIC_API_KEY=unused opencode\n```", "url": "https://wpnews.pro/news/red-hat-openshell-podman-fedora-rhel-vertex-ai-anthropic-quickstart", "canonical_source": "https://gist.github.com/maxamillion/177a36f959911900e6f2a1f625cdcc3a", "published_at": "2026-06-01 19:07:35+00:00", "updated_at": "2026-06-02 23:14:03.837535+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-tools", "ai-infrastructure", "large-language-models", "generative-ai"], "entities": ["Red Hat", "OpenShell", "Podman", "Fedora", "RHEL", "Vertex AI", "Anthropic", "Claude Code"], "alternates": {"html": "https://wpnews.pro/news/red-hat-openshell-podman-fedora-rhel-vertex-ai-anthropic-quickstart", "markdown": "https://wpnews.pro/news/red-hat-openshell-podman-fedora-rhel-vertex-ai-anthropic-quickstart.md", "text": "https://wpnews.pro/news/red-hat-openshell-podman-fedora-rhel-vertex-ai-anthropic-quickstart.txt", "jsonld": "https://wpnews.pro/news/red-hat-openshell-podman-fedora-rhel-vertex-ai-anthropic-quickstart.jsonld"}}