Privacy-first, self-hosted real-time speech-to-speech translation.

Semantic ifs from open models, on a 3090 at home. Independent; not affiliated with Jev or TypeSafe.

Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.

A studio for image and video generation — one prompt bar, each model’s own settings, and every finished run in one gallery.

A calm agent multiplexer with familiar IDE features, for macOS.

Open source AI clip generator: turns long videos into viral 9:16 shorts with AI moment detection, face tracking, subtitles and dubbing. Self-host free with Docker (MIT), or use the cloud with GPU s…

OpenClaw skill for BTC 5-minute Polymarket momentum trading with configurable risk controls and optional hedge logic.

Invert scroll direction for physical scroll wheels while maintaining "Natural" scrolling for trackpads on MacOS

C++/GGML conversion of VAST-AI SkinTokens; Auto rigs a mesh ready for animation

A self-improving RLM agent for coding workflows and long-running autonomous tasks.

利用 AI 大模型和自动化工作流，根据主题或关键词一键生成高清短视频。Generate HD short videos from a topic or keyword with an automated AI workflow.

Publish your AI coding-agent usage (Claude Code, Codex, Gemini CLI, etc. via ccusage) as a shareable snapshot on usage.fyi

SkyReels-V2: Infinite-length Film Generative model

Claude Design DESIGN.md prompts by aesthetic family, remix recipes, skills, video teardowns, X signal, honest community takes.

🎨 Best DeepSeek Harness Design Plugin. The open-source Claude Design alternative. 🖥️ Local-first desktop app. 🖼️ Your coding agent becomes the design engine: prototypes, landing pages, dashboards, …

The design language that makes your AI harness better at design.

Run your GitHub Actions locally 🚀

LEAKED SYSTEM PROMPTS FOR CHATGPT, CLAUDE, GEMINI, GROK, PERPLEXITY, CURSOR, LOVABLE, REPLIT, AND MORE! - AI SYSTEMS TRANSPARENCY FOR ALL! 👐

Notes and operating profiles for working with AI coding agents.

Orchestrate multiple coding agents from desktop and mobile

Official Python inference and LoRA trainer package for the LTX-2 audio–video generative model.

VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.

The only tool you need to know what is happening and how to fix it.

🛰️ Track token usage across AI coding agents from your terminal. 🏅 Global leaderboard with trillions of tokens tracked.

An image-to-world skillset for Claude.

An AI skill that provides design intelligence for building professional UI/UX across multiple platforms.

Lightning-Fast, On-Device, Multilingual TTS — running natively via ONNX.

Transformer Explained Visually: Learn How LLM Transformer Models Work with Interactive Visualization

3D Gaussian Splat Editor