Build Anything with Antigravity CLI, Here’s how!
The video introduces Anti-Gravity CLI, a tool Google launched at IO 2026 to replace Gemini CLI, which enables multiple AI agents to run in parallel on different tasks simultaneously. The presenter demonstrates three practical multi-agent workflows applied to managing a community called the AI Profit Boardroom. The core argument is that parallel AI workflows represent a fundamental shift from the one-prompt-at-a-time model most users currently rely on.
Summary
The video opens by announcing that Google shipped Anti-Gravity CLI at IO 2026 as a direct replacement for Gemini CLI, which was fully retired for individual users as of June 18th, 2026. Unlike traditional AI tools that handle one prompt at a time in a conversational back-and-forth, Anti-Gravity CLI operates by accepting a high-level goal, breaking it into subtasks via an orchestrator agent, and spawning individual sub-agents that execute those subtasks simultaneously in parallel.
The presenter walks through three concrete workflow examples, all framed around managing a membership community called the AI Profit Boardroom. The first workflow addresses community growth by running four agents in parallel: one researches current AI automation trends, one writes social media content positioning the community as a solution, one generates coaching call engagement questions, and one drafts a welcome message for new members. The presenter claims this produces a week's worth of community content in roughly 90 seconds.
The second workflow automates new member onboarding. Given a new member's goal or interest area, three agents run simultaneously to create a personalized 7-day roadmap, draft direct messages to relevant existing members, and generate a set of custom prompts for that member's use case. The presenter highlights that Anti-Gravity CLI supports scheduled background tasks, meaning this workflow could be triggered automatically every time someone joins, with no manual intervention.
The third workflow is a content repurposing system. One core topic or module launch is fed into four agents at once: one writes a YouTube script outline, one creates short-form video hooks for Instagram and TikTok, one writes a member email, and one generates ten community post ideas. The presenter frames this as replicating what a full content team does, compressed into a single terminal command.
The video also notes that Anti-Gravity CLI shares its agent harness with Anti-Gravity 2.0, meaning improvements to the underlying model automatically improve CLI-based workflows without any user action. The presenter closes by promoting the AI Profit Boardroom community and the AI Success Lab as resources for learning to build these multi-agent systems.
Key Insights
- Google retired Gemini CLI entirely and forced migration to Anti-Gravity CLI as of June 18th, 2026, signaling to the presenter that AI infrastructure is changing at a fundamental level, not just at the tool layer.
- Anti-Gravity CLI uses an orchestrator agent that receives a high-level goal, breaks it into subtasks, and spawns individual sub-agents each with its own context to run those subtasks simultaneously rather than sequentially.
- The presenter argues that the time cost of AI workflows is not the difficulty of individual tasks but the sequential execution of multiple simple tasks, and that parallelizing them collapses hours of weekly work into minutes.
- Anti-Gravity CLI supports scheduled background automation, meaning workflows like new member onboarding can be triggered automatically without manual initiation, which the presenter distinguishes as the difference between 'using AI' and 'building AI systems.'
- Anti-Gravity CLI shares its agent harness with Anti-Gravity 2.0, so every future improvement Google makes to the core model is automatically applied to CLI-based workflows without requiring any action from the user.
Topics
Transcript
[0:00] Build anything with anti-gravity. CLI, here's how. Google just shipped something at IO 2026 that most people completely missed. It's called anti-gravity CLI and it's not just a new tool, it's a new way to run an entire operation with AI. This is what happened. Google killed Gemini CLI, completely retired it. And in its place, they shipped anti-gravity CLI, a terminal-based system built entirely around one idea, running multiple AI agents at the same time on different tasks in parallel. As of June 18th, [0:30] 2026, Gemini CLI stops working for all individual users. Google is forcing the migration. That's how serious they are about this. So, what does anti-gravity CLI actually do? Here's the simplest way to…
Full transcript available for MurmurCast members
Sign Up to AccessMore from Julian Goldie SEO
NEW Nvidia Autonomous AI is WILD!! 🤯
Nvidia announced Nemo Clo, a new autonomous AI agent system that operates independently without continuous prompting. Powered by Nemotron 3 Ultra (a 550 billion parameter model), the system is five times faster and cheaper than previous versions, with OpenShell providing secure sandboxed execution.
Laguna XS 2.1: New FREE + Opensource Local AI!
Julian reviews Laguna XS 2.1, a new free open-source local AI coding model from Poolside that performs comparably to Qwen 3.6 and outperforms Claude Haiku on benchmarks. He demonstrates its practical capabilities by building landing pages and functional apps, highlighting its speed, offline functionality, and multiple deployment options through local setup, Claude Code, or OpenRouter's free API.
How to Run Hermes FREE Forever!
The video demonstrates how to run the Hermes AI agent for free using Gemma 4, a local open-source model from Google, with significant speed improvements through MLX optimization. The setup works on Apple Silicon Macs or via free APIs on Open Router, enabling autonomous agents to work offline and privately without subscription costs.
This NEW Chinese AI is INSANE! (FREE + Open Source!)
Long Cap 2.0 is a new open-source Chinese AI model from a food delivery app company that offers 1 million tokens of free context memory, beats GPT-4.5 on SWE bench pro benchmarks, and uses efficient parameter activation to reduce computational overhead while maintaining high performance.
Claude Code is now FREE: Here’s how…
Google's new Gemma 4 model running on Ollama is 90% faster on Apple Silicon, enabling free Claude Code usage locally without token costs. The setup requires three simple steps: downloading Ollama, Gemma 4, and installing into Claude Code, with alternatives available via OpenRouter API for non-Mac users.