Local AI on four Macs: MLX capacity, speed and trust boundaries
Local AI gets a hardware question before it gets a leaderboard question: can the model and its working memory fit on the machine? Apple's distribute…
Open Source
⚑ Report a ProblemLatest Open Source news from Tech News
All topics
AI
agents
ai
api
architecture
automation
backend
beginners
career
database
devchallenge
devops
discuss
javascript
linux
llm
machinelearning
mcp
opensource
performance
productivity
programming
python
react
security
showdev
testing
tutorial
typescript
webdev
One MCP config for Claude Code, OpenCode and OMP
Three files for one server You use Claude Code for one task and OpenCode for another, and both should see the same Figma and Linear MCP servers. Eac…
Тревожная беседа с агентом
Человек я уверенный. Правильнее даже самоуверенный. Будучи таковым я знал, что больше среднего осведомлен в ИТ безопасности. Ключи, менеджеры пароле…
От чата c LLM к полноценному AI-агенту: пошаговая настройка OpenCode
Когда я впервые начала использовать AI в работе, сценарий был довольно стандартным: открыть чат, вставить текст, сформулировать запрос, получить отв…
Как настроить Arch Linux, чтобы он обошёл Windows 11 по производительности и стилю
Работа с Linux часто отпугивает начинающих пользователей, но зря. Linux — не сложная система. Она просто другая. Чтобы с ней было удобно работ…
OpenCode Needs Memory, Not Another Background Pipeline
I kept explaining the same project facts to new OpenCode sessions. Not the durable rules that already belonged in AGENTS.md . Those were present. Th…
The Portability Trap: When 'It Loads' Doesn't Mean 'It Works'
I ran a skill migration and nothing broke. Or so I thought. Break 3 in my migration diary noted that skills degraded silently. This is the deep dive…
Loaded Obeyed: Why Your Agent Quotes Rules It Doesn't Follow
The file was loaded. The rules just weren't followed. Here's the two-failure diagnostic that tells you which one you have — and what to do for each.…
Kimi K3 in OpenCode: What One Finished Coding Task Actually Cost
Kimi K3 launched with impressive benchmark results—and a lot of debate about its price. For developers using coding agents, however, price per milli…
I audited my own AI-generated refactor and found 46 bugs. Here's what that taught me.
How a 1,920-line file turned into 410 lines, why "it works" was a lie twice, and why the fix wasn't a smarter model — it was a gate that doesn't tru…
pkg-cache — простой локальный кеш пакетов
Пример реализации простого кэширующего прокси для пакетов npm, composer и pip на базе node.js для Windows и Linux. Читать далее
Разговариваем с датчиками на человеческом: как связать MQTT, TimescaleDB и LLM через Model Context Protocol (MCP)
А что, если не писать сложные SQL-запросы, не выгружать логи в CSV и не строить графики в Python? Просто спрашиваете у AI-агента: «Покажи максимальн…
I Built Two AI Tools. The Second One Told Me How I Should Be Learning AI.
The Problem TeachSim taught me LangGraph because the bot had to actually work, with real conversations running through it. GitHub Digest taught me a…
AIналитик v2 по BABOK: как я переписал AI-платформу для бизнес-анализа, чтобы она работала c любыми LLM
Спойлер: архитектура AIналитика полностью переписана, теперь Платформу можно запускать практически под любым харнесом (OpenCode, Kodik, Codex, Claud…
Agentp: Turn OpenCode Into a Headless AI Engine for Your Editor, Terminal, and Telegram
I've always felt out of step with the prevailing trends. Before the AI explosion, the mantra was "ship fast" — the Minimum Viable Product. If you we…
PewDiePie: разбираю self-hosted AI-workspace, который собрал 47 тысяч звёзд за пару дней
PewDiePie последние полтора года ушёл из развлекательного контента в технику: домашний сервер, локальные LLM, self-hosting. Результат — репозиторий…
OpenCode review 2026: the open-source terminal coding agent that challenges Claude Code
This article was originally published on aicoderscope.com TL;DR : OpenCode is an MIT-licensed, provider-agnostic terminal coding agent with 167k Git…
One Tool That Cuts Token Costs 40-80% for Claude Code, Codex, opencode, and openclaw
The problem isn't your prompts If you're running Claude Code, Codex, opencode, or openclaw and the API bill keeps climbing, you've probably tried wr…
/disconnect for opencode — a tiny TUI plugin I wish existed before I made it
I use opencode as my daily TUI coding agent. It's good. But there's one thing that kept biting me. When you want to remove a single provider — say y…
Agentic LLM Inference Parameters Reference for Qwen and Gemma
This page is a practical reference for agentic LLM inference tuning (temperature, top_p, top_k, penalties, and how they interact in multi-step and t…
Give Your AI Persistent Memory: OpenCode + MemPalace in 10 Minute
The Problem Every OpenCode session starts from scratch. Your AI doesn't remember past conversations, decisions, or solved problems. You repeat conte…