Meefik's Blog

Freedom and Open Source

agent.sh: an LLM agent in busybox

17 Nov 2026 | ai linux shell

Most LLM agent harnesses assume a normal machine: a Python or Node runtime, a package manager, a writable /tmp. None of that exists on the devices I actually care about — an ARM board with a read-only root, an embedded target where the only thing in /bin is busybox. I wanted an LLM agent that still works there.

So I wrote agent.sh: a single-file LLM agent in ash (busybox’s POSIX shell). One executable, only busybox applets — no jq, no python, no curl. It speaks the OpenAI tools protocol natively: the model asks for a tool, the harness runs it, feeds the result back, and loops until the model answers in plain text.

The agent.sh tool loop: model → tool call (shell, skill, delegate, mcp) → harness runs it → result back, looping until the model answers in plain text. Badges: only busybox applets, no jq/python/curl, read-only root OK.

talkdeck: AI-made narrated decks

06 Nov 2026 | ai nodejs

I wanted to hand a topic to an AI agent and get back a video presentation — narrated, with a talking head in the corner — not a PDF I then have to record and present myself. The static slide is the well-solved, commodity half: Marp turns Markdown into a clean HTML deck and a PDF. What’s missing is the narration and the face, and the part that has to be scriptable if an agent is going to produce it at all.

So I wrote talkdeck: a small Node CLI on top of Marp Core that turns a Markdown deck into a 1080p video with a voice-over and a lip-synced talking head. The point is that the whole thing is drivable from the command line — no UI, no manual steps — because the goal is that an agent writes the file and runs the command.

The demo above was made that way: an agent wrote the slides.md and ran one command. The voice is a clone of a fifteen-second sample, and the face in the corner was lip-synced to the same audio.

E-paper TTY for CrowPanel ESP32-S3

04 Aug 2026 | diy

I got a CrowPanel ESP32-S3 — it’s a 5.79” e-paper display with the ESP32-S3 built in, USB-C powered, all in one board. The screen is big enough to be useful and small enough to sit on my desk without being obnoxious.

The obvious thing to do with an e-paper display that holds its image with zero power is write something to it and leave it alone. So I wrote papertty: firmware that listens on USB serial and renders whatever text you pipe to it. Basically a physical tty backed by paper.

The display runs at 272×792 in B&W — two SSD1683 panels stitched together via SPI. Firmware is Arduino/C++, built with PlatformIO. Nothing exotic.

Source on GitHub. There’s also a demo video if you want to see it actually working instead of trusting my word for it.

Peerix Talk: P2P video app in 13 evenings

20 Jul 2026 | peerix webrtc javascript

I wanted to build a P2P video chat app. Nothing fancy at first — just something that works and doesn’t rely on some company’s servers in the middle.

I gave myself 30 evenings (because this was strictly an after-work project), which felt generous for a side thing. It turned out I could’ve been more ambitious: with a local LLM as my pair programmer inside Zed, I shipped it in 13 days.

Here’s how that went down, what the AI actually helped with (and what it didn’t), and why I bother running models locally at all.

Peerix Talk app

You can try Peerix Talk or look at the source on GitHub.

Set up self-hosted LLMs for local development

18 Jun 2026 | amdgpu ai benchmark linux

I’ve been gradually adding local LLMs to my daily workflow, and now I’ve got a setup that runs AI agents right inside Zed Editor for coding. This post walks through the whole stack — from GPU acceleration to editor integration — so you can set something similar up for yourself.

local-dev

Peerix: WebRTC development made simple

08 May 2026 | peerix webrtc javascript

Today, I’m excited to introduce Peerix, a JavaScript/TypeScript library designed to simplify WebRTC development. Peerix abstracts away the complexities of WebRTC, allowing developers to focus on building their applications without worrying about the underlying signaling and peer connection management. With Peerix, you can easily create peer-to-peer applications for video conferencing, file sharing, gaming, and more. Whether you’re a seasoned WebRTC developer or just getting started, Peerix provides a straightforward API to help you get up and running quickly. Check out the comprehensive documentation and start building your next WebRTC application with Peerix today!

Peerix

Time Warp Scan on pure JavaScript

30 Dec 2025 | javascript

The New Year 🎄 is almost here, and what better way to celebrate than with a fun coding project? Today, I’m excited to share a simple Time Warp Scan implementation using pure JavaScript and HTML5 Canvas. Have fun, and happy New Year! May your coding be productive.

Time Warp Scan

AI Podcast from scratch with open-source tools

10 Dec 2025 | ai comfyui

The pace of AI development is exhilarating, with new models and capabilities emerging constantly. Recently, I upgraded my PC with a new AMD GPU and have been exploring its power with local Large Language Model (LLM) tasks. Today, I’m taking on a far more complex challenge.

I set out to create an entire five-minute AI-generated podcast using only open-source models and tools. The entire process ran on my computer, completely bypassing expensive, privacy-compromising cloud services. The goal was to test the absolute limits of quality and feasibility for a fully self-hosted media production.

The result? The “Humanless Podcast”. Take a look at what came out of this experiment (click to play).

Humanless-Podcast

I will now walk you through the entire, eight-step process of creating a podcast like this, from the initial script to the final video.

LLM performance on AMD Radeon AI PRO R9700

15 Nov 2025 | amdgpu ai benchmark linux

Recently, I acquired an AMD Radeon AI PRO R9700 to enhance my machine learning and development setup. It is a powerful GPU designed for professional workloads, including machine learning and AI applications. In this post, we explore the performance of large language models (LLMs) on the R9700, highlighting its capabilities and benchmarks.

chart

Serverless WebRTC conferencing with E2E encryption

05 Oct 2025 | webrtc javascript

Building reliable, privacy-respecting peer-to-peer conferencing can be surprisingly simple when you split responsibilities cleanly: media transport (WebRTC) and signaling (a tiny transport for exchanging SDP and ICE). I built a minimal library to demonstrate that split and to enable serverless workflows using whatever signaling channel you prefer — from in-memory drivers for demos to NATS-based pub/sub for distributed apps.

This post describes the library’s purpose, core design, how to use it, and a practical example of a NATS signaling driver with end-to-end encryption using the browser Web Crypto API.

demo

Just try it out: demo | source code