NEW Claude Update is INSANE! 😱
The video introduces Anthropic's new Claude CLI (Ant CLI), explaining how it provides a simpler way to access Claude's API without writing code. The presenter demonstrates how it differs from Claude Code, outlines key business use cases, and shows how they've integrated it into their 'Agent Operating System' to manage AI agents in the cloud.
Summary
The video begins by introducing the newly launched Ant CLI for Claude, positioning it as a powerful tool for managing AI agents in the cloud. The presenter distinguishes between using Claude via the chat interface (a single human typing into a box) versus using the API, which allows businesses to run Claude autonomously inside their own software without human intervention.
The presenter uses an analogy to clarify the difference: using Claude chat is like ordering coffee at a counter, whereas the Ant CLI and API together are like a pipe that pumps coffee straight into a factory all day with no barista needed. The API is described as the 'doorway' that lets software talk to Claude directly, while the CLI is 'a much easier way to knock on that door.'
Several business use cases are outlined for why a company would want API access: auto-answering customer support emails, summarizing uploaded documents, running Claude overnight across company data to find patterns, or building an entire product with Claude wrapped in a custom UI. None of these use cases are possible through a chat interface alone.
The presenter then explains the evolution from the 'old way' (writing Python or JavaScript scripts to send API requests) to the 'new way' (typing a single terminal command via the Ant CLI). Key CLI capabilities highlighted include: testing prompts quickly without building full scripts, running automated tasks on servers with no human present, piping Claude's output into other terminal tools, and managing cloud-based agents with version-controlled configuration files.
The distinction between Claude Code and Ant CLI is clarified: Claude Code is an agent that builds things (e.g., writes and edits code for a website), while Ant CLI is a remote control for the API. They are described as complementary — Claude Code uses the Ant CLI under the hood when building API-dependent tools.
The presenter then demonstrates how they have integrated the Ant CLI into their proprietary 'Agent Operating System,' showing live examples of pulling model lists, checking auth status, viewing managed agents, browsing previous sessions, and accessing uploaded files — all from a single CLI interface rather than navigating through multiple web console pages. A live demo shows an SEO strategist agent being given a keyword task and returning an actionable content plan through the cloud via the Ant CLI. The video closes with a promotion for their paid community and training platform.
Key Insights
- The presenter argues that the Ant CLI is not competing with Claude Code but is complementary — Claude Code actually uses the Ant CLI internally when building tools that require API access, because the CLI is 'simple and predictable.'
- The presenter claims that the Ant CLI removes the need for coding knowledge to access Claude's API, stating that users can now send API requests with a single terminal command instead of writing Python or JavaScript scripts.
- The presenter demonstrates that integrating the Ant CLI into their Agent Operating System allows all agent management tasks — viewing models, sessions, files, and agent status — to be done from one CLI, eliminating the need to navigate through multiple pages of the Claude web console.
- The presenter highlights session tracing as a key Ant CLI feature, explaining that after kicking off an agent session you can pull a trace to inspect all the reasoning steps the agent took, providing transparency into autonomous cloud agent behavior.
- The presenter suggests that Claude Code is well-suited to operate the Ant CLI itself, meaning users can instruct Claude Code in natural language to execute CLI commands, further reducing the need for technical expertise.
Topics
Transcript
[0:00] and the CLI has just been launched for Claude and this is a really powerful way to use AI agents and manage them inside a claude. So I'm going to show you exactly what it works, what's different now, how to use it, etc. and how to implement it inside your business plus a powerful way that brings it all together. So essentially we've already plugged ants CLI directly into our agent operating system. You can see a bunch of agents that we've created right here and this is very different from using Claude code normally. I'll come on to that in a second, but you can basically manage [0:31] your AI agents in the cloud, which is very…
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.