Search

Native augmented reality for React Native — world & face tracking, plane detection, hit-testing, and 3D content on iOS (ARKit) and Android (ARCore), powered by Nitro Modules.

dsh plugin: a compact_now tool letting the model trigger compaction itself at a safe point, plus a context_status tool so it can check real token usage against its context window, instead of only the automatic token-threshold trigger.

Model-free /trim for DeepSeek Harness — drop the oldest, least valuable span of context on demand (the `/trim` command) or automatically when a request hits the model's context wall, without any model call.

Tiny zero-deps project scaffolder: local + git templates, {{vars}}, pm install

DevPreFlight Flat UI Component Kit & Scaffolder for React 19, Next.js & Tailwind CSS

The Intelligo CLI: scaffold an AI SaaS app, generate owned source, and check its migrations and upgrades.

Command-line client for aile.sh — lend spare AI capacity from a machine you own, or choose which lender serves your requests.

AI-powered git commits with smart grouping, project rules and multi-provider support

Autourgos LLM wrapper for the OpenAI Chat Completions API

Local-first CLI for assisted translation with translation memory, glossary propagation, Git integration, and LLM providers.

Turn any AI conversation into a portable context card. Local-first via Ollama. CLI companion to the Context Transfer macOS app.

Run DeepSeek Harness command execution in OpenSandbox containers: an OpenSandbox-backed ctx.subprocess and container-world ctx.sandbox for dsh.

Claude-compatible memory for DeepSeek Harness: a user-chosen memory directory with MEMORY.md index and topic files, the memory tool, and a settings page

Typed client and benchmark harness for Jev, TypeSafe's System One decision model, through the Vercel AI Gateway. Answers 'is Jev good enough for my data, and where do I set the threshold?' with one command.

Official JavaScript/TypeScript SDK for Wan 3.0 multimodal AI video generator, text-to-video, and document-to-video studio.

🎬 从想法、分镜到 AI 视频素材的导演 Skill，附本地工作台与中文图文手册

Liquid Glass - Powered by WebGPU/WebGL.

Sub-50ms conversational turn-taking and interruption engine eliminating voice AI latency pauses with Jev System 1

React components, design tokens, and interface contracts for q1travel products.

DynamoDB state adapter for Chat SDK: thread subscriptions, distributed locks and caching on a single table, no Redis, no VPC