The long-horizon computer-use harness. Run AI agents across desktop apps and the CLI for extended periods while preserving task state and making reliable progress on complex workflows. Features fresh-context execution, durable verified state, independent auditing, recoverable progress, and native Claude Code / Codex / OpenClaw integration.
给 AI 编码 agent 用的 skill 集合，Claude Code 和 codex 都能跑。novel-characters：把小说拆成角色设定集——人物画像、卡通形象提示词、音色提示词、三视图。 | Skills for AI coding agents, working in both Claude Code and codex. novel-characters turns a novel into a character bible: profiles, cartoon-design prompts, voice prompts and turnaround sheets.
Swiftlet is a Swift and Metal runtime that runs large Qwen Mixture-of-Experts models locally on Apple devices by streaming expert weights from storage, enabling 35B and 80B models to run with low RAM, including on iPhone.
Desktop app that records your on-screen work session and uses the GitHub Copilot CLI to reconstruct it as an intent + ordered steps, then builds a reusable Skill or Automation for Microsoft Scout, Microsoft Copilot Cowork, or Copilot Studio.
Spectrum-based acceleration for ComfyUI’s native MiniMax H3 audio-video model. Forecasts post-transformer features with Chebyshev ridge regression to skip selected transformer evaluations, with adaptive scheduling, sampler-aware safeguards, CPU/VRAM history storage, and native fallbacks.
Run the full 2.78-trillion-parameter Kimi K3 model beyond available RAM by streaming activated weights directly from NVMe. A dependency-free, embeddable C inference engine.
