Fetching from the wire…
01
02
03
04
05
06
07
08
OSS2026-09-04 · source-backed
The Document Foundation posted September 3 that the exclusion is deliberate, because no integration meets all its requirements. The six: user choice of inference location (local, self-hosted or independently selected), no document transmission without explicit authorization, no telemetry on AI features, open multi-provider interfaces to prevent lock-in, generated content in ODF rather than a proprietary format, and full optionality including absence from the UI for non-users. Third-party extensions connecting to local Ollama-style models remain available. That's the most specific procurement checklist anyone has published for evaluating an AI feature, and it's usable outside LibreOffice. The Document Foundation
Each link below shares sources, entities, or timing with this story.
For about a year, "run your agent locally" meant accepting a model that couldn't reliably call a tool twice in a row. That excuse is gone. Meta Superintelligence Labs published Muse Glimmer today: a 29.6B dense causal transformer, 52 layers, 6,656 hidden dim, with a ~1.8B ViT-...
The July 6 release delivers nearly 90% faster Gemma 4 token generation through multi-token prediction with automatic draft-length tuning, on by default, output-preserving, no config (Ollama). It also adds MLX-engine support for more model families and flash attention for older...
Google released open-source Multi-Token Prediction (MTP) drafters for the Gemma 4 model family. The concept: pair a heavy target model (Gemma 4 31B) with a lightweight drafter that predicts several future tokens in parallel. The target model verifies the predictions in a singl...
magnitudedev/magnitude recommends models that fit your hardware, then downloads, tunes and serves them to Pi, OpenCode, Hermes, OpenClaw, Codex, Claude Code, Oh My Pi and Cline. Since the August 21 coverage, it cut three CLI releases inside 44 hours: 0.0.9 on September 1 at 07...
Three moves, two days, no coordination between them. August 10–11: GitHub shipped Ollama as a BYOK provider inside Copilot for JetBrains (GitHub Changelog). Unsloth released Unsloth Desktop with a command literally named unsloth start claude, which points Claude Code and Codex...
Chetan Conikee released it August 29 under Apache-2.0, a Homebrew-installed CLI that keeps you in Codex or Claude Code while delegating well-specified jobs to Luna, Qwen3 or open-weight models through Ollama, with the frontier model reviewing the cheaper result. Its four rules...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.