AUTOMATER NEWSROOM

What’s changing.
Why it matters.

New tools, useful workflows, and consequential AI developments.

Subscribe via RSS ↗

Latest briefing

Oct 21, 2026, 2:49 PM EDT
GitHub Next's Proof-Driven Development Kit Asks Rust's Verus Verifier to Check AI-Written Code, Not a Reviewer
GitHub Next and Microsoft Research's Proof-Driven Development Kit turns a plan into a formal Verus spec, then proves agent-written Rust code matches it, falling back to tests and computer-use agents when a proof isn't possible.
Oct 21, 2026, 1:00 PM EDT
Recursive's Flint Lands in Ollama: An Apache-2.0, 40B MoE Coding Model Built for Agent Work
Ollama's v0.40.8-rc0 pre-release adds Recursive's Flint: an Apache-2.0, 39.8B-parameter MoE with about 2.5B parameters active per token, a 262K-token context and day-zero launch lines for Claude Code and OpenCode. What local agent operators should verify before giving it a default slot.
Oct 21, 2026, 10:52 AM EDT
Cloudflare Turns on WebMCP for Nearly 100,000 Commerce.com Storefronts
Cloudflare says almost 100,000 Commerce.com storefronts now expose typed shopping tools to agents via WebMCP, with per-merchant edge opt-outs. What is live, what is still experimental.

Browse all →

Flint moves repository tasks through a 39.8B-parameter sparse model into Ollama's rc0 packaging, which launches it inside Claude Code, OpenCode, Hermes Agent and OpenClaw lanes on macOS.

October 21, 2026

Recursive's Flint Lands in Ollama: An Apache-2.0, 40B MoE Coding Model Built for Agent Work

Ollama's v0.40.8-rc0 pre-release adds Recursive's Flint: an Apache-2.0, 39.8B-parameter MoE with about 2.5B parameters active per token, a 262K-token context and day-zero launch lines for Claude Code and OpenCode. What local agent operators should verify before giving it a default slot.

Our AI-assisted editorial method · Explore our in-depth Intel guides