September 1, 2026
Explore FastVideo, an open framework combining sparse attention, distillation, scalable training, and real-time video generation across GPUs and Apple Silicon.
A local Claude Code workflow that evaluates jobs, tailors applications, verifies PDFs for ATS systems, and prepares candidates for interviews.
Tencent’s WeMM-Embedding models unify text, images, video, and visual documents in one embedding space, with strong benchmark results and flexible dimensions.
StemDeck is an open-source, local-first stem extraction studio that isolates vocals, drums, bass, guitar, and piano with no cloud subscriptions or uploads.
Tailcat brings Tailscale's magicsock and WireGuard data plane to a lightweight, userspace CLI tool without requiring central coordination.
Generate stereo 48 kHz music locally with HOT-Step CPP, a feature-rich C++/GGML interface for ACE-Step, audio tools, plugins, and model training.
Discover how a 176KB C99 binary runs a 2.78-trillion-parameter Kimi K3 model on a single CPU with just 8.24GB RAM, using streaming, MXFP4, and clever memory management.
Explore Decimen Optical Transfer, an open-source tool that streams files between devices using animated QR codes and fountain coding, achieving up to 130 KB/s with no network connection.
anydoc is a fast Rust library that converts Word, PowerPoint, Excel, PDF, and more to clean Markdown. With Node.js, Python, and WASM bindings, it's the fastest and most complete converter available.
Microsoft's Skill Recorder captures your screen activity and uses GitHub Copilot CLI to turn it into reusable Skills or Automations for AI agents. Learn how it works and how to install it.
Discover WASTE, a dependency-free C inference engine that streams expert weights from NVMe to run the full 2.78T-parameter Kimi K3 on consumer hardware at 0.6 tok/s.
K3Flight runs the 2.8T-parameter Kimi K3 model on CPU with only ~55GB RAM by streaming weights from storage via cPilot Runtime. A single-file Linux inference server.