Open Source Radar: August 7 — agent skills & coding agents heat up

Skills went from niche to default this week: Addy Osmani's engineering pack passed 80k stars, and the trending board filled out with terminal coding agents and agent-infrastructure tooling. Four open-source projects worth running, plus a watchlist.

DeepSeek-Reasonix (Go, ~33k stars) — A DeepSeek-native coding agent for the terminal, engineered around prefix-cache stability: repeated context hits the cache instead of the bill, so long-running sessions stay cheap. That's the differentiator — most agents burn your context window on re-reads; this one is built to be left running. It's the strongest DeepSeek-native answer to Claude Code yet.

openwork (TypeScript, ~21k stars) — The open-source alternative to Claude Cowork, built on opencode. Anthropic's multi-agent workspace is closed and hosted; openwork gives you the same shared multi-agent coding setup you can self-host and fork. If you want Cowork-style collaboration without the lock-in, this is the week's best option.

agent-skills (JavaScript, ~84k stars) — Addy Osmani's collection of production-grade engineering skills for coding agents: testing, code review, performance, and more, packaged so an agent can load them on demand. It's the clearest proof yet that skills are the new plugins — a reference library that turns a generic coding agent into one that behaves like a senior engineer.

cloudflare/computer (TypeScript, ~5.5k stars) — Cloudflare's answer to "give your agent a computer": a virtual filesystem living inside a Durable Object, with pluggable runtimes that project that state into a container, an isolate shell, or JavaScript isolates. State is authoritative in SQLite; execution is swappable. It's preview-only and explicitly not production-ready, but it's the most interesting bet this week on where agent workspaces go.

Worth watching next week: TencentDB-Agent-Memory and PrimeIntellect's prime-agent keep climbing, and if the skills pattern holds, expect Google's official skills repo to pull the rest of the majors in.

Which of this week's projects are you actually going to try? Tell us in the comments.

Sources: DeepSeek-Reasonix (GitHub) · openwork (GitHub) · agent-skills (GitHub) · cloudflare/computer (GitHub)

Akhetonics says its all-optical CPU reaches a customer in 2026

Light-based computing keeps promising more than it delivers — but one Munich startup has just put a date on its bet, and the interview laying it out is doing the rounds on Hacker News this week. Akhetonics says it will deploy its first commercial machine with a major customer by the end of 2026, with several more planned for 2027. The company, founded by Michael Kissner and Leonardo Del Bino, is building a computer where data enters as light, is switched as light, and circulates through memory

The Week in AI — October 5–11, 2026

Every big claim this week turned out to rest on fine print more interesting than the headline: revenue only the company reporting it can define, safety tests sandboxed while the product keeps the web, and a Pentagon phase-out nobody would confirm until reporters kept asking. The week's top 5 1. OpenAI's revenue was $20 billion below the numbers everyone quoted — and the gap was definitional. The Financial Times reported Thursday that OpenAI's annualized revenue runs roughly $20 billion unde

Drone strike shuts a third Yandex data center, taking YandexGPT offline

Russia's largest tech company is learning what the AI era's infrastructure war looks like from the receiving end — three data centers in four days, and with them much of the cloud layer Russian businesses run on. A Ukrainian drone strike knocked out Yandex's data center in Vladimir early Sunday morning, the third of the company's facilities hit since October 8. The site — reported at roughly 50 MW and designed for about 2,880 server racks — stopped operating completely after the attack, Yandex

Agent teams cost up to 5x more, barely score higher

The multi-agent hype train hit a benchmark this weekend — and the grid and the trucking regulators had quiet weeks of their own. Vals AI put agent teams head-to-head with single agents on its Vibe Code Bench, and the teams cost between 1.8 and 5.1 times more for almost no extra quality. The evals company ran GPT-6 Sol and Claude Opus 5.5 solo and in teams across 50 apps at two reasoning efforts; out of four comparisons, only one was statistically significant — Sol at medium effort, where the t

Read more

Akhetonics says its all-optical CPU reaches a customer in 2026

The Week in AI — October 5–11, 2026

Drone strike shuts a third Yandex data center, taking YandexGPT offline

Agent teams cost up to 5x more, barely score higher