Who says the terminal has to be boring?

Recently, I stumbled across some stunning e-paper displays online. You know the ones—sleek, grid-based layouts showing live stock market numbers and crypto rates. It got me thinking: what if we could replicate that exact aesthetic natively in the terminal using Coni?

As it turns out, it’s not just possible—it’s incredibly easy.

Thanks to Coni’s built-in ui-mount primitive, we don’t have to mess around with raw ANSI escape codes or manual cursor positioning. We just declare our UI state, map it to a layout tree, and let the engine do the heavy lifting!

Imagine sitting in your REPL, writing code, and suddenly forgetting how a standard library function works. Or maybe you need a quick algorithmic implementation, but you don’t want to switch context to a browser or a separate AI chat window.

What if your programming language itself could introspect its own codebase, write code for you, and evaluate it live in your REPL memory?

Today, we’re thrilled to introduce the Coni Introspection Agent—a natively integrated, tool-calling LLM agent built directly into the Coni language ecosystem. And because we know developers love their modern IDEs, we’ve also packaged it with a native Model Context Protocol (MCP) server.

Picture this: You see a shiny new Open Source LLM drop on HuggingFace. It promises to be the next big thing in local reasoning. You want to try it out on your MacBook. So you spin up your terminal.

You pip install some packages. You get an error about torch being compiled without Metal support. You switch to conda. You update your environment. You wait 15 minutes for 4 gigabytes of dependencies to download. You run the Python script. You get a ValueError: weight shape mismatch because your transformers library is exactly 0.0.1 versions out of date. You update transformers, which breaks accelerate.

The Model Context Protocol (MCP) is rapidly becoming the gold standard for connecting Large Language Models to external tools and data sources. Historically, if you wanted to build an MCP client or server, you needed to reach for heavy, bloated SDKs in Node.js or Python, dealing with complex asynchronous state and dependency hell.

We thought: What if we could do it entirely natively in Coni?

In this post, we’re going to walk through how we brought a complete, zero-dependency MCP Client and Server directly into the Coni standard library (mcp.coni). It’s fast, highly concurrent, and ridiculously easy to use.

Let’s face it: writing 2D browser games from scratch can be a total drag. Between managing Canvas contexts, handling asynchronous asset loading, and dealing with Javascript’s eccentricities, you often spend more time wrestling with boilerplate than actually designing your game.

Enter Namakemono—our incredibly cute and dangerously fast 2D game framework built natively in Coni targeting WebAssembly.

The Single State Philosophy

One of the biggest headaches in game development is state management. Do you keep your player, enemies, and projectiles in separate variables? What happens when an enemy needs to check the player’s position?

In our ongoing quest to make Coni the most capable, dependency-free, and relentlessly fun functional language out there, we’ve hit a massive milestone. We didn’t just write an AI script—we went fully native.

Today, we’re unveiling our first fully native AI example: The Poem Generator.

Using the highly capable Qwen 2.5 0.5b instruct model formatted as a raw GGUF binary, this new Coni script takes a theme, invokes a local LLM, computes a beautiful poem, and spits out characters at a shockingly fast rate of over 70 tokens per second (TPS).