tmux is a terminal multiplexer built for humans managing remote servers. It splits a terminal into panes, keeps sessions alive across disconnections, and lets you attach and detach from running processes. Sysadmins have used it this way since 2007. What makes tmux interesting for agents is something more fundamental: every tool that runs in a...
Category: Technology
mcpx: Because MCP Servers Shouldn’t Require a PhD in Protocol Plumbing
The Model Context Protocol has won. Since Anthropic open-sourced it in late 2024, MCP has grown to 97 million monthly SDK downloads, over 10,000 active servers, and first-class support from every major AI platform. Google adopted it. OpenAI adopted it. The Linux Foundation now governs it through the Agentic AI Foundation. If you're building...
reWritable: Software that knows how to change itself
When I built clive, the core insight was deceptively simple: don't give the agent a list of tools. Give it an environment.An API is a call-response primitive. You invoke it, it returns something, the state lives somewhere else. An environment is a thing you inhabit. You enter it, act inside it, leave it different than...
Clive Can Now Modify Itself
We've been building clive — a CLI Live Environment that gives an LLM a terminal and a keyboard. The core idea is simple: instead of wrapping tools in APIs and schemas, you let the agent read the screen and type. The terminal becomes the interface. The loop becomes the protocol. We've added something that takes...
The Terminal as Agent Interface: Introducing clive
There is a quiet assumption embedded in most agent infrastructure: that agents need structured interfaces. APIs, schemas, tool definitions, protocols like MCP or A2A. The assumption is that the gap between an LLM and a system needs to be bridged by something machine-readable. clive starts from a different assumption. LLMs are excellent at reading text...
Your Agent Framework Is a Monolith. The Browser Doesn’t Care.
Last week, I dropped an LLM agent into a plain HTML file. No Node.js. No Webpack. No Docker container running a Python backend that proxies to another Python backend. One <script type="module"> tag, a couple of imports, and an agent that reasons, calls tools, writes code, and delegates to sub-agents — all orchestrated entirely client-side,...
The Web Has No API for Agents – Agentic Microformats
In February 2026, we pointed a browser-embedded AI agent at a demo e-commerce store and asked it to buy a laptop stand. It read the site's discovery file, parsed the page metadata, extracted six products with prices and availability, added three items to the cart via API, updated a quantity, removed one item, checked that...
The AI That Pauses to Think: How Interleaved Reasoning Is Reshaping Autonomous Agents
When Moonshot AI demonstrated its Kimi K2 model tackling a PhD-level mathematics problem in hyperbolic geometry, according to examples published in their technical documentation, the AI didn't just compute an answer. It embarked on a 23-step journey: searching academic literature, running calculations, reconsidering its approach based on results, querying databases again, and iterating until it...
The LLM Whisperers: How Cloudflare and Anthropic Cracked the Code on AI Agent Efficiency
There's a delicious irony at the heart of modern AI development. We've spent years training large language models on every scrap of code humanity has ever written—Stack Overflow answers, GitHub repositories, programming textbooks, documentation—teaching them to become fluent in Python, JavaScript, TypeScript, and dozens of other languages. Then, when it comes time to actually use...
AI Hallucinations: Why They Happen and How We’re Tackling Them
AI hallucinations refer to instances where a model generates a confident response that sounds plausible but is factually incorrect or entirely fabricated . For example, an AI chatbot might cite a nonexistent legal case or invent a scientific-sounding explanation out of thin air. These aren’t intentional lies – they result from the way generative AI...
