Tencent fully open-sources HY-World 2.0, a four-stage pipeline that turns a text prompt or image into a navigable, game-engine-ready 3D world — not just a video.
A community contributor packaged samuelcardillo's 35B mixture-of-experts model into GGUFs that bundle a multi-token prediction head, unlocking self-speculative decoding from a single file.
NVIDIA open-sources a full reference stack that turns raw video streams and archives into searchable, summarizable, agent-queryable data using VLMs and MCP tools.
A LocalAI quantization bundles the multi-token prediction head into a single GGUF, giving Claude-distilled Qwen3.6 self-speculative decoding without a draft model.
xAI ships the biggest update yet to X's open-source For You algorithm, adding a runnable local inference pipeline and a downloadable pre-trained Phoenix model
video-use lets coding agents edit raw footage into a polished final.mp4 using transcripts, ffmpeg, and a self-correcting render loop — no timeline editor required
A community-built MCP server hands Claude, Cursor and Windsurf deep knowledge of 2,541 n8n nodes so agents can design, validate and deploy real workflows.