# yeet blog, raw Markdown index Every published post as a raw Markdown file. Fetch any URL below to read its source. 15 posts, newest first. - [Is Your Jellyfin Actually Using the GPU? Ask the Kernel](https://yeet.cx/blog/is-jellyfin-using-the-gpu.md): Jellyfin's dashboard says Transcoding whether Quick Sync is doing the work or your CPU is. The kernel knows which: the ffmpeg it spawned either holds /dev/dri/renderD128 open or it doesn't. We wrote jellytop on yeet, a top for Jellyfin transcodes that reads the fd table, the argv and the CPU ticks of every encoder on the box, and ran it on an N100 with hardware acceleration on, off, and misconfigured. 2026-10-01, Jacob Pradels, 9 min read. - [Nobody Is Listening on Port 8125](https://yeet.cx/blog/nobody-is-listening-on-8125.md): An app fires StatsD datagrams at a port with no listener and Grafana shows the request rate anyway. We replaced prometheus/statsd_exporter with 165 lines of eBPF and a JavaScript decoder on yeet: the kernel reads the datagram, a sandbox with no sockets counts it, and Prometheus scrapes the result. First in a series on replacing every exporter with one binary. 2026-09-30, Jacob Pradels, 7 min read. - [Interview with Julian Goldstein, Founder of yeet](https://yeet.cx/blog/interview-with-julian-goldstein.md): yeet founder Julian Goldstein on making machines readable by machines: why logs, metrics and traces all make you guess the question in advance, how a V8 runtime pointed at 7,000 kernel trace points gives agents hands on a Linux box, and what gets built when observability, networking and security turn out to be the same thing. 2026-09-29, Necco Ceresani, 24 min read. - [Your SBOM Is Fan Fiction](https://yeet.cx/blog/your-sbom-is-fan-fiction.md): Your SBOM describes a machine that does not exist. We built a runtime bill of materials on yeet that asks the kernel what is actually executing, which shared objects each process has mapped, and whether the function named in an open advisory is actually in memory, across a fleet, from a sandbox that can't leak. 2026-09-24, Jacob Pradels, 12 min read. - [We Put an L7 Firewall in the Kernel](https://yeet.cx/blog/l7-firewall-in-the-kernel.md): Application-layer firewall decisions at XDP, before a socket buffer exists. We built a firewall that decides on HTTP/2 headers in the kernel with eBPF and lets you write the policy as a JavaScript app. Matching a header costs under 200ns, the request around it costs microseconds, and it runs on cleartext HTTP/2 behind TLS termination. Here's how it works and what we measured. 2026-07-06, Jason Evans, 9 min read. - [File Shield + Flight Recorder: How Yeet Stops the Trivy Attack Pattern with eBPF](https://yeet.cx/blog/flight-recorder.md): The Trivy attack exfiltrated credentials from 10,000+ CI/CD pipelines by reading files it already had access to. We fed the incident report into yeet's AI and built a kernel-level block in hours. Here's what we built — and why it matters for every team running AI coding agents on their infrastructure. 2026-04-03, Necco Ceresani, 8 min read. - [What is eBPF? How It Works in the Linux Kernel (Simple Guide)](https://yeet.cx/blog/what-is-ebpf.md): What is eBPF? A simple, non-technical explanation of how eBPF works, why it matters, and how tools like Yeet make kernel-level observability, security, and networking accessible with JavaScript. 2026-04-01, Necco Ceresani, 5 min read. - [The Advantage of Yeet: A Programmable Kernel Runtime for Bespoke Observability and Agentic Infrastructure](https://yeet.cx/blog/the-advantage-of-yeet.md): Yeet is a programmable kernel runtime that combines eBPF, JavaScript, GraphQL, and AI agents in a single Linux daemon. It replaces generic observability dashboards with bespoke instrumentation tools — custom-built for each application, with kernel-depth visibility, deployed in minutes. Yeet is the first platform where AI agents can read, query, and act on live infrastructure at the kernel level. 2026-03-26, Necco Ceresani, 10 min read. - [The Observability Industry Has the Wrong Customer: Why AI Agents Need a New Stack](https://yeet.cx/blog/ai-agents-observability.md): The observability industry is built on one invisible assumption: a human is looking at the data. Every design decision — dashboards, static alerts, pre-aggregated metrics, advance instrumentation — follows from that assumption. Two simultaneous shifts are breaking it: production systems now move faster than humans can observe, and AI agents can reason about structured data without any of the affordances the current stack was built to provide. Together, these shifts don't just demand faster tooling — they make the current architecture the wrong abstraction entirely. This post lays out what observability looks like when the primary consumer can reason, and the five first-principles design choices that follow. 2026-03-26, Necco Ceresani, 10 min read. - [You Are The BIOS Now: Building A Hypervisor In Rust With KVM](https://yeet.cx/blog/you-are-the-bios-now.md): Opening up a black hole just to say 'Hello, World!' 2025-07-29, Julian Goldstein, 20 min read. - [Lock-Free Rust: How to Build a Rollercoaster While It’s on Fire](https://yeet.cx/blog/lock-free-rust.md): A joyride through the dangers of lock-free programming. 2025-05-12, Julian Goldstein, 15 min read. - [What Is Yeet?](https://yeet.cx/blog/what-is-yeet.md): yeet is a platform for easy, just-in-time observability of Linux systems. 2025-04-16, Julian Goldstein, 5 min read. - [Typescript Trees](https://yeet.cx/blog/typescript-trees.md): Expressing data constraints with type-level magic. 2025-04-03, Ben Dean, 5 min read. - [BPF from Scratch in Rust](https://yeet.cx/blog/bpf-from-scratch-in-rust.md): How to write a BPF program from scratch in pure Rust. 2025-04-03, Julian Goldstein, 10 min read. - [How do I audit a Github Action with Yeet?](https://yeet.cx/blog/audit-actions-runner.md): Do you know what each action is doing on your system? 2024-10-01, Jacob Pradels, 5 min read.