ExecuTorch vs TVM vs LiteRT: 2026 on-device AI shootout

Why three frameworks, and why now If you want to run a neural network on a phone, a Raspberry Pi, a smart toaster, or a laptop without a beefy GPU, you used to have one reasonable choice: TensorFlow Lite. In 2026 you have three serious ones — ExecuTorch, Apache TVM, and LiteRT (the renamed TensorFlow... » read more

AI Coding Agents in 2026: A Roundup for Linux Devs

dean
Walk into any 2026 developer’s terminal and you’ll find at least one AI coding agent already configured. The space moved faster than most people tracking it could follow: terminal-native agents have overtaken IDE plugins for serious engineering work, open-source caught up to commercial tools feature-for-feature (mostly), the Model Context Protocol is the de facto standard... » read more

Goose on Linux: Block’s Open-Source Coding Agent

dean
Goose started as Block’s internal coding agent, then moved to the Linux Foundation’s Agentic AI Foundation (AAIF) in late 2025. Apache-2.0, written in Rust, distributes as a single static binary with no Node runtime, no Python runtime, no Electron. The latest stable is v1.42.0 (2026-07-13). Where Claude Code is for solo power users and Cline... » read more

Cline in VS Code: Plan + Act for Real Engineering

dean
Cline is an open-source (Apache-2.0) autonomous coding agent that runs inside VS Code. It edits files, runs commands, and asks for approval at every meaningful step. The latest stable VS Code extension is v4.0.8 (2026-07-11); the parallel CLI build is at v3.0.40 (2026-07-13). Compared to Claude Code and OpenCode (which are terminal-first), Cline lives where... » read more

Aider on Linux: The Terminal-Native Coding Agent

dean
Aider is the OG terminal-native AI pair programmer — Apache-2.0, runs on Python, mapped your repo for context long before “agentic loops” became the marketing term, and commits its own changes to git by default. The latest release is v0.86.0 (2025-08-09); the project is in maintenance mode but still functions. This article shows the install... » read more

OpenCode on Ubuntu: A Self-Hosted Coding Agent

dean
OpenCode (formerly sst/opencode, now anomalyco/opencode) is a provider-agnostic, open-source terminal coding agent. It’s MIT-licensed, has provider adapters for Anthropic, OpenAI, Google, Bedrock, Vertex, Groq, and any OpenAI-compatible API (Ollama, LM Studio, OpenRouter), and at v1.17.20 it ships with a polished TUI, multi-session support, and an LSP-aware edit pipeline. This article shows the install, the minimum... » read more

Claude Code on Linux: A Practical Setup Guide

dean
Claude Code is Anthropic’s terminal-native coding agent. It reads your project, edits files, runs commands, and handles git — all via natural language. The latest stable release as of writing is v2.1.209 (2026-07-14). This article walks through installation on Ubuntu 22.04/24.04, the recommended daily-driver workflow, and the configuration patterns that show up most often in... » read more

Hermes Desktop on Linux: The GUI for Hermes Agent

dean
Hermes Desktop is the Electron GUI companion to the Hermes Agent CLI. It launches the same agent/ core that runs in your terminal, just wrapped in a chat window with a sidebar, file previews, and provider settings. If you’ve already installed Hermes CLI (see the companion article), the desktop is one command. This piece covers... » read more

Hermes Agent on Linux: Install + First-Run Setup

dean
Hermes Agent is Nous Research’s open-source assistant that runs the same agent core across a CLI, a TUI, an Electron desktop, and ~20 messaging platforms (Telegram, Discord, Slack, Feishu, and others). It learns across sessions via memory and skills, runs scheduled jobs, delegates to subagents, and drives a real terminal and browser. This article walks... » read more

Run Qwen3 and MiniCPM5-1B Locally on Linux with llama.cpp (2026 Guide)

dean
title: “Run Qwen3 and MiniCPM5-1B Locally on Linux with llama.cpp (2026 Guide)” date: 2026-07-14 categories: [“linux-software”] tags: [“llama.cpp”, “qwen3”, “minicpm5”, “local-llm”, “ai”, “ollama”, “ubuntu”, “fedora”, “arch”, “gpu-inference”] Run Qwen3 and MiniCPM5-1B Locally on Linux with llama.cpp (2026 Guide) In 2026, running a real large language model on your own Linux machine is no longer exotic.... » read more