The AI tools worth your time. One email a week.

The tools, reads, and big-lab releases that actually matter. Each gets a one-line verdict from an engineer who ships.

What you'll get — straight from issue #9

Star of the week

DeepSeek Harness (dsh) agents open source

DeepSeek's own agent harness, MIT, built on Cordis and organised so that everything — including the desktop and the Web UI — is a plugin. `npx @deepseek-ai/dsh web` starts a local server on 127.0.0.1:3080 and opens it; the README labels the whole thing a developer preview and warns in capitals that compatibility-breaking changes are coming.

172,000 stars in the seven days since the repo appeared on 13 August, and the ecosystem grew faster than the harness did: a curated plugin list at 10.5K, a Web UI skin-and-plugin collection at 5.1K, an in-harness plugin market, and a desktop port at 16.2K — all created the same week. A lab whose reputation was built on weights spent this release shipping the runtime instead, and the plugin topic did the rest.

anti-slop coding open source

Fifteen opinionated Oxlint rules that reject low-evidence TypeScript and JavaScript: chained type assertions, `unknown` parameters and returns, runtime `typeof` checks, module mocking, widen-then-assert. It is meant to be vendored rather than depended on — an agent skill copies the plugin in, merges the lint config, and then the files are yours to edit.

Every one of these rules is a review comment somebody is tired of writing. Moving them into the linter means the argument happens once, at config time, instead of in every pull request — and the ignore list, which names ten different agent directories, tells you exactly which authorship problem the rules were written for.

OpenBot infra open source

CopilotKit's agent platform for your own infrastructure: Docker Compose brings it up, data sits in your Postgres, no model ships in the box, and the admin's credential is encrypted at rest. Each bot gets a computer of its own — a real browser with its own logins, its own files, and only the tools you grant — and anything it does to a computer, file, or MCP server passes through a single gateway that decides before and records after. Any AG-UI agent can be dropped in as a coworker.

Per-agent isolation plus one auditable chokepoint is the same shape the serious infrastructure keeps converging on, and here it is as MIT alpha you can run on a laptop. It is early enough that the README says so twice, so treat it as the architecture to read rather than the thing to depend on.

Cumora productivity open source

Cross-platform team chat — Electron, PWA, iOS, Android — where agents sit on the same roster as humans, with personas and memory, their own DMs, a shared Kanban board and calendar, and real email in and out. Brains come from either managed per-agent pods on the OpenAI Responses API or BYOA, where `npx cumora agent computer` pairs your own Mac or VPS and the agent runs on your local Claude Code or Codex; the server never sees your provider keys.

2.7K stars in the three days since it appeared, and the BYOA path is the interesting half: your subscription, your machine, their interface. Whether agents belong in the team chat or in a queue somewhere is still an open argument, but this is the most complete answer anyone has shipped to the first option.

Plus the reads and big-lab releases — read issue #9 in full →

Previous issues

Or browse every past issue — no paywall, the email just gets there first.

Skip the scroll. Keep the signal.

I read the launches, changelogs, and hype threads so you don't have to — and send only what survives the filter. Curated by @aimorsels.