Ollama 0.40.2 Stable and LM Studio 0.4.26
Quiet tooling releases matter more than model launch theater. On October 8, Ollama 0.40.2 landed as stable — MLX as the default on Apple Silicon, out…
Category
AI & Agents
Follow AI & Agents via RSSMellum2.1: JetBrains’ Fast Open Coding Model
JetBrains shipped Mellum2.1 on October 8 — a 12B MoE coding model with about 2.5B active parameters, Apache 2.0, trained with RL in real repositories. It…
Garuda: Coding Agents Sandboxed by the OS
Most “agent sandboxes” are polite suggestions. Garuda (announced October 8) takes the grown-up route: Seatbelt on macOS, bubblewrap on Linux, no network by default, an audit…
Which Open-Weight Model to Self-Host This Month
Model shopping is a trap if you chase every launch post. GenAI Brief’s October 2026 open-weight roundup is a useful shortlist: Gemma 4, gpt-oss, Mistral Medium…
DeepSeek Harness v0.2
DeepSeek’s agent runtime grew up. Harness v0.2 (developer preview, late September 2026) ships the first official desktop installers for Apple-silicon macOS and 64-bit Windows. Same MIT-licensed…
Magnitude
Magnitude is not another chat window. It is an open-source inference engine for local agents that tunes kernels on your hardware before a model runs. The…
Pi 1.0
Earendil shipped Pi 1.0 on October 1, 2026 — a hardened, minimal, MIT-licensed terminal coding-agent harness you can actually depend on. Hundreds of thousands of people…
Cursor Projects: Stop Herding Agents
I spend a lot of my days in Cursor with cloud agents and local subagents. The pain was never “can an agent write code?” — it…
Dyad: Local Open-Source App Builder
Dyad is the local answer to Lovable / v0 / Bolt: describe an app, get runnable code, keep the files on your disk. Open source (dyad-sh/dyad,…
Point Codex Desktop at Ollama
Same Codex desktop — diffs, review mode, browser annotations, Git worktrees. Different brain. Ollama’s Codex App integration lets you keep OpenAI’s coding UI while inference runs…