AI Coding Live News

At 08:30 UTC on November 9, Omarchy creator DHH released v0.5.0 of omarchy-local-ai, the local model engine behind Omarchy. It extends local model support to 64 GB NVIDIA GB10 / N1x-class machines and makes Nemotron 3.5 Bolt the default for that tier (project measurements: full 262K context, 91 tok/s on short prompts and 82 tok/s at 32K, peaking under 40 GiB). About 20 minutes later he posted on X that Omarchy 4.6 will recommend the best model each machine can run, showing the agents panel on the Ryzen AI Max+ 495 machine AMD gave him, with a Claude Code subscription next to a local Qwen3.8 Flash Next using 94 GiB. The feature comes from PR #17267, merged November 1: one omarchy agent local use best command picks a model by GPU family and RAM class and runs it in a rootless Podman container with no network access, for coding agents such as OpenCode and pi. No release date for 4.6 has been announced.

Zoom

Japan's Preferred Networks (PFN) released PLaMo 3.0 Fin (plamo-3-8b-fin-instruct) on Hugging Face on November 9 under the PLaMo Community License. Built on PLaMo 3 NICT 8B Base, co-developed with NICT, it went through continued pre-training on finance corpora, SFT and DPO. It writes its reasoning in Japanese before answering, supports OpenAI-style function calling and can run on a single GPU in private clouds or on-premises. Per PFN, its average on the Japanese finance benchmark japanese-lm-fin-harness rose from 48.0 to 55.8, ahead of Gemma 4 E4B (45.6) and gpt-oss-20b (43.0) but behind Qwen3.5-9B (60.1) and Ministral 3 14B (62.8). SFT ran on PFN's in-house MN-Core 2 AI chip, and a coding agent helped port the training code in under a week.

Zoom

Researchers from Fudan University, Alibaba (Alibaba Token Hub) and other institutions published Co-Design Bench on arXiv (2610.35138, submitted 2026-10-26), and from November 8 it spread widely on X. It takes 273 web-app revision tasks that real users had to request repeatedly, drawn from 26,314 real coding sessions and 37,463 deduplicated queries (100 multimodal editing tasks and 173 repository editing tasks), each paired with hidden expert-written acceptance criteria, 2,331 in total. Ten models were run in the same Claude Code harness. The best, GPT-6 Astra, met 69.9% of criteria per task on average but passed every criterion on only 26.4% of tasks; Claude Opus 5 reached 18.3% and Grok 4.6 just 6.6%. The paper tested September-era models, so newer ones such as Opus 5.5 and GPT-6.1 are not included.

Zoom

Open WebUI, the self-hosted AI chat platform with about 158K GitHub stars, published v0.13.1 on GitHub at 11:07 UTC on 2026-11-08. The headline change: on an Open Terminal that offers agents, coding agents such as Claude Code, Codex and Pi now appear in the model picker, where you can chat with them, call them by voice, pick reasoning effort and service tier, and approve their tool requests in the chat. It also introduces Tether, a desktop companion app for macOS, Windows and Linux that ties your own computer to Open WebUI so models and agents can work in your real files and repositories, reachable from any browser including a phone. Tool chats no longer rewrite the system prompt each round, so provider prompt caches can hit; the project says they now cost much less. About 45 minutes later v0.13.2 fixed a UUID error when serving over plain HTTP.

Zoom

Google and the University of Waterloo posted ReproBridge on arXiv (2611.08452, 2026-11-05). It turns the code fixes, environment setup, launchers and guide an agent discovers while reproducing a paper into a standardized artifact. ReproBridge-Bench covers 36 papers, 387 experiments and 1,029 tasks. Author-reported: across Sonnet 4.6, Sonnet 5, Opus 5 and Gemini 3.8 Flash, mean success rises from 76.4% to 92.6% and API spend drops 19.7% on average.

Zoom

On 2026-11-05 Microsoft Foundry blogged that Foundry Local CLI 0.13.0+ can run 4-bit Qwen3.8-27B (~18 GB weights) on-device via ONNX Runtime and connect it to GitHub Copilot through Bring Your Own Key. Needs an NVIDIA GPU with at least 24 GB VRAM (about 64K context on 24 GB; up to the model's 262K max on 32 GB+). Vendor-cited model-card scores include Terminal-Bench 2.1 73.0 and SWE-bench Pro 61.7; Microsoft also reports higher generation speed than same-quant llama.cpp on RTX 5090 and DGX Spark. Mac and AMD support are still on the roadmap.

Zoom

On 2026-11-07 the official OpenCode account announced Browse: an MCP server plus Chromium extension that lets agents drive your local real browser with existing tabs, logins, and extensions. Sensitive steps such as login, 2FA, or payment hand the tab back until you click Continue. It works with Chrome, Edge, Brave, Arc and other Chromium browsers, and with MCP clients including OpenCode, Claude Code, Cursor, Codex, and Zed. Source is MIT at anomalyco/browse; the npm package is @opencode/browse.

Zoom

On 2026-11-06, Cursor's changelog shipped Voice Chat with Agents: realtime two-way voice calls with coding agents in the Agents Window, IDE, web, and iOS. Dictation remains a separate feature. Grok Voice handles listening and speaking (voices include Ara, Eve, Leo, Rex, Sal); the coding agent still uses the model you picked. With Privacy Mode on, voice chat runs with zero data retention. A signed-in Cursor account is required (API-key-only sessions cannot start a call).

Zoom

On 2026-11-05, Hugging Face Harness Optimization researcher Joël Niklaus (@joelniklaus) released the Harness Leaderboard: same model, provider, and reasoning effort with only the harness swapped, covering GLM-5.3-Flash, DeepSeek-V4.1-Flash, and Flint on Terminal-Bench 2.1 and DeepSWE—28,849 trials and about $4,746 of inference. Author-reported averages: mini-swe-agent ~51.4% resolve rate; Pi ~49.4% at about $0.29 per solved task. This is an individual research leaderboard, not a Hugging Face company product announcement.

Zoom

On November 3 (US Pacific time), Vercel launched Security Review in public beta. It is a new Vercel Agent capability alongside Code Review and Investigation: once enabled, every push to connected GitHub repositories triggers a diff-only vulnerability review that finishes in seconds. Findings land in the Security dashboard, PR comments and the CLI, and can be fixed with one click by Vercel Agent or pulled into your own coding agent via vercel security vulnerabilities. It is available to Pro and Enterprise teams, and reviews are free until November 10.

Zoom

On Oct 31, Benji Taylor, head of design at X and SpaceXSI, released Stageshow on X: an open-source skill (MIT license) for coding agents that helps them produce faux product UI that looks real, including stills, cursor demo animations, and bento grids, delivered as ordinary React components. It installs with one command, and he says it works with Grok Build, Claude Code, Codex, Gemini, and others. The launch post drew about 4,500 likes and 6,500 bookmarks. He notes it rarely nails a demo in one shot and most still take a few rounds of feedback.

Zoom