Use Your Mac for AI Agents: Self-Host Gemma 4 12 B with Pulumi and Tailscale
Self-host multimodal Gemma 4 on a Mac with Pulumi, llama.cpp, and Tailscale, using Unsloth's Gemma 4 12 B Q8 GGUF with a 128K context window.
Pablo Seibelt

Page 5 of 82
Self-host multimodal Gemma 4 on a Mac with Pulumi, llama.cpp, and Tailscale, using Unsloth's Gemma 4 12 B Q8 GGUF with a 128K context window.
Pablo Seibelt

Build EKS-hosted vCluster test environments with Pulumi, EKS Auto Mode, Helm, RBAC, quotas, and safe cleanup workflows.
Pablo Seibelt

See why teams choose Pulumi over Terraform for modern infrastructure as code, with examples for refactoring, secrets, testing, and safer changes.
Pablo Seibelt

AI coding has two shapes: 2x is mostly prompting, 10x is mostly plumbing. The parallel coding playbook, translated to Pulumi.
Engin Diri

Pulumi Service Provider v1.0 generates its pulumiservice:api/* surface from Pulumi Cloud's OpenAPI spec at runtime, so new features land without provider PRs.
Luke Ward

In a large codebase, the model is the smaller variable. The harness around it does the work: CLAUDE.md, hooks, skills, LSP, MCP, subagents.
Engin Diri

GPU clouds, MLOps platforms, and AI-powered infrastructure tools, compared. What each one is good at, where it falls short, and how to pick in 2026.
Alex Leventer

The new pulumi do command lets you create, read, update, and delete any cloud resource across the full Pulumi ecosystem with a single, agent-friendly API.



4 authors

Mention @pulumi-neo in GitHub or @Neo in your Slack workspace to bring Pulumi Neo into the threads where your team works on infrastructure.
Pulumi Neo Team

Schedule any Neo task on a cadence. Drift checks, provider freshness, and encryption audits run themselves and deliver results as pull requests.
Pulumi Neo Team

Page 5 of 82