Z.ai Opens ZCode as 3.14 Adds Scripted Subagent Workflows
ZCode 3.14 adds scripted subagent workflows and full-access controls as Z.ai opens its desktop, web and terminal agent code under Apache-2.0.
DeepSeek, Kimi, Qwen, and Chinese models reshaping the race.
ZCode 3.14 adds scripted subagent workflows and full-access controls as Z.ai opens its desktop, web and terminal agent code under Apache-2.0.
Qwen Live Harness connects realtime voice and vision to Codex, Claude Code and other agents, but access, privacy and approvals require careful setup.
Qwen3.8 LiveTranslate streams translated speech and text, understands 60 languages and can separate speakers. See its limits, pricing and deployment checklist.
Qwen Studio brings reasoning, multimodal input, generation, code and Artifacts to web, mobile and desktop. Here is what the overview confirms.
LLaDA-UI is a 16.7B diffusion vision-language model that turns native-resolution interface images into structured GUI actions.
Ling-3.0-flash-VL has 124B total parameters, 5.5B active parameters and two benchmark scores tied to different index versions.
Tencent AuK is a 1.5B open speech model for generation, editing, enhancement and separation. AuK-Flash uses four inference steps.
MiniCPM5-2B is a dense local AI model with 131K context, GGUF and MLX builds, open data and a sampling warning developers should know.
GLM-5.3-Flash combines 320B total parameters, 18B active parameters, native multimodality and 1M context. Here is what that means for deployment.
Qwen Code 0.23.4 adds Agent Board coordination, web previews, cross-session messaging and goal limits. Review the breaking changes before upgrading.
Qwen-Drive 1.0 combines a 4B vision-language model with perception and planning heads. Here is what is open, what fits on 24GB, and what is…
GLM-5.3 is a 756 GB open-weight release. Cloudflare and Vercel now offer hosted routes for testing quality, latency and cost before self-hosting.