There are so many coding agents these days, but one of these things is not like the other. And let's be honest, a lot of them are not only similar in
features, they're actually starting to look like each other. Similar to how most people can't distinguish Pepsi from Coca-Cola on a blind taste test,
coding agents are similar where if I hide the logo from anti-gravity, codeex, and cursor, it's
really hard to tell which one is what. And one agent that stands out is Pi. And a lot of people who use Pi seems to swear by it. So, how does this
framework that powers OpenClaw stand out against other coding agents that are out there? Welcome to Caleb Bright's Code, where every second counts.
Quick shout out to MicroEnter. More on them later. Most people probably heard of Pi as the brain that
runs OpenClaw. But why isn't OpenClaw powered by a much more comprehensive agent like Codeex CLI, Gemini CLI, or even Clot Code? Don't these offer
more tools out of the box? What makes Pi unique is more about what an agent isn't than about what an agent is. It's kind of like how negative space in
art focuses on the empty space around the subject rather than trying to draw the object itself. Okay,
what does all of this mean? Pi is notorious for how much it leaves out instead of how much it adds in. It doesn't have sub aents out of the box. It
doesn't have MCP. It doesn't have background bash and it doesn't use to-do list. The real benefit of PI is when it comes down to its ability to extend
its own harness. In conventional coding agents like Cloud Code, Codeex, and anti-gravity, you can't
really change its own harness. Sure, you can configure settings around their harness, but you can't really extend its own harness. A good example is
using hooks. In case you don't know what a hook is, it's a mechanism that allows you to interrupt the tool call chain either before or after to
perform specific action you want it to do. So if I wanted to make my agent write an audit trail every time
it deletes a folder through a tool call, I can just add a pre-tool use hook to write an audit trail by mechanism. And in the case of clot code, adding
a hook means you're adding this within the settings.json file for clot code to parse and consume all within the predetermined harness. But in the case
of Pi, instead of a setting file in JSON, PI writes an entire TypeScript code as an extension of
its own harness natively in code. So the PI agent actually extends its own harness while being self-aware at the same time. And once I run the /reload
command in the terminal, PI will now incorporate the newly written code as a hook. So you can imagine how this can be used to build applications like
openclaw by building around pi and adding the scaffolding around it like mcps integrations with
messaging applications gateway for hosting and more. And as you can see openclaw can just either import portions of pi's components or use the
terminal user interface as the module. So then what exactly is the use cases of pi? Should people ditch and cloud code and jump into pi instead? But
first, a quick word from MicroEnter sponsoring this video. As someone who's working in the AI industry, I
really need the right hardware for the job, whether it's for local inference, fine-tuning, or building my own custom agent here at home. And all these
things require parts like GPUs, RAM, CPUs, and storage. MicroEnter helps you get the product you need, like a list of graphics cards that you can see
specifically curated for AI workloads that typically need large amounts of VRAM and fast
interconnect. Beyond dedicated graphics cards, I can also shop for solidstate drive since most models nowadays need to run as GGUF, which means you
need to have a good hard drive to support your locally run inference. For more generic use cases like building agents, I can also shop for Mac Studios
or the DJX Spark for a simpler hardware to run everything I need for building agents. MicroEnter is
opening brand new store in Austin, Texas later this year. You can sign up for a free 128 GB flash drive in store. And if you're in Columbus, Ohio, you
can sign up for a free 128 gigabytes flash drive at their remodel. They also have news column on their website that shows different thought
experiments and relevant materials around AI. Link in the description below. While Frontier coding agents
like Cloud Code, Codeex, and anti-gravity might be mutually exclusive, and you might prefer to only use one as your primary engine, PI is more of a
framework than a purely a coding agent. When we look at Pi's implementation, it componentizes into four segments following the computer science
principle separation of concerns where each component handles different abstractions of problem and it also
uses open close principle from the solid principle where it's open for extension and closed for modification by design. For example, all the
complicated logic and implementation for dealing with completions API from various providers is all in the PI AI folder. This means all the tedious
work in working with API messaging between providers like Enthropic, OpenAI, Google, SpaceX and Open Router.
All of these providers for tracking tokens, tool calling, reasoning, and streaming are all in this specific component. This means all the code that's
involved in talking to various APIs and even switching providers, mid conversations are all contained in this component. The agent folder handles the
agentic loop that handles validation, event streaming, and tool execution. And the coding agent in
the TUI is what the user interacts with on the front end where you have the terminal that renders text, manages sessions and custom tools and themes.
An architecture like this allows people to build their own applications like OpenClaw using PI as a framework and even create their own agent like the
code review agent or research agent that are meticulously built to be efficient as opposed to
trying to guide a bloated agent like cloud code and writing these in the form of a prompt and customizing the harness that comes with it. Now you
might be wondering why all of this is necessary. It might seem like Pi is just going out of the way to try to keep it minimal. I mean, out of the box,
it just doesn't really come with a lot of stuff, and it requires me to build things on top of it to get
it working. What's even the point of using Pi in the first place? Personally, I find that Pi is the ultimate hedge against changing harness in agents.
We have examples like Langchain that was rewritten over four times in its architecture. Manis was rewritten five times over, showing just how volatile
the agentic layer in harness actually is. As the underlying models get better in tool calling,
requiring us less implementation to be done to work around the limitations around the model and the concept of build to delete meaning what we build
today might be obsolete so soon. And by building less and avoiding overengineering in the harnessing layer, it positions for the best long-term
durability.