Neo, Now in the Terminal

Why It Matters

Bringing Neo to the terminal removes friction for DevOps teams, enabling AI‑driven infrastructure management within existing workflows and accelerating adoption of agentic IaC.

Key Takeaways

• Pulumi Neo now runs via `pulumi neo` CLI in terminal
• Leverages existing auth, kubeconfig, and environment variables locally
• Supports approval, permission, and plan modes identical to cloud version
• Enables handoff from Claude Code or Codex through Neo skill
• Integration catalog (Atlassian, Datadog, Linear, PagerDuty) works locally

Pulse Analysis

The rise of generative AI has reshaped how infrastructure‑as‑code (IaC) tools are used, shifting from static scripts to conversational assistants. Pulumi Neo, the company’s AI‑powered agent, originally lived in the Pulumi Cloud console where it could scaffold, migrate, and troubleshoot resources. By launching a native terminal command, Pulumi bridges the gap between cloud‑centric AI and the command‑line environments where most engineers spend their day, delivering a seamless, context‑aware experience that feels like an extension of the existing CLI.

Running `pulumi neo` locally means the assistant automatically inherits the developer’s authenticated sessions, kubeconfig files, and environment variables. This eliminates the need for separate branches, credential provisioning, or manual context copying, dramatically reducing setup time. The same granular controls—manual, balanced, or auto approval modes, read‑only versus write permissions, and a dedicated plan mode for safe exploration—apply in the terminal just as they do in the cloud UI. Moreover, Neo can be invoked by other AI agents via the Neo handoff skill, allowing Claude Code, Codex, or similar tools to delegate infrastructure tasks without leaving the current workflow.

For enterprises, the move signals a broader shift toward “agentic infrastructure,” where AI agents act as collaborative partners rather than isolated tools. By integrating with Pulumi’s existing integration catalog—covering Atlassian, Datadog, Linear, PagerDuty, and more—organizations can embed AI assistance directly into their CI/CD pipelines and incident response processes. The ease of local execution is likely to boost adoption among DevOps teams seeking faster, more reliable automation, positioning Pulumi as a front‑runner in the next generation of AI‑enhanced cloud management.