OpenClaw 2026.9.5 adds Atomic Updates, plugin hot reload, read-only conversation sharing, GPT Live in meetings, and specialist-agent setup.

TypeSafe AI's Jev returns typed decisions with calibrated probabilities instead of text, at $0.042 per 1M input tokens.

Linkup Research releases SPARSEUP, an open-source 149M-parameter sparse embedding model scoring 56.4 nDCG@10 on BEIR-13 under ...

Meta has released Muse for Mac, the first version of Muse that can complete things on a user’s computer. The agent works with ...

Qwen3.8-LiveTranslate cuts average lag to 2.3 seconds across 60 languages, adding speaker diarization, bilingual display, and ...

Qwen has released Qwen3.8-LiveTranslate, a real-time simultaneous interpretation model built on a new Interleave architecture. It cuts average lagging (LAAL) from 2.8 seconds to 2.3 seconds. It also ...

PrismML's Ternary Bonsai 2 27B compresses Qwen3.8 27B to 5.93 GB, retaining 98.2% benchmark performance under Apache 2.0.

Compare 11 open-source agent harnesses for local LLMs, including OpenCode, Pi, Goose, Cline, OpenHands, Aider, and Codex CLI.

Alibaba’s Qwen team has released Qwen3.8-Omni-Flash. They called it its first omni-modal model built around agentic capabilities. It accepts text, images, audio, and video, and it returns text.

Spinning up a flashy prototype with an LLM has never been easier, but in production, building an agent is just the opening 10% sprint. The real marathon, the brutal 90% that determines whether ...