Stars
Memory and context engine + app that is extremely fast, scalable, and can be run fully locally. The Memory API for the AI era.
LEAKED SYSTEM PROMPTS FOR CHATGPT, CLAUDE, GEMINI, GROK, PERPLEXITY, CURSOR, LOVABLE, REPLIT, AND MORE! - AI SYSTEMS TRANSPARENCY FOR ALL! 👐
A gallery that showcases on-device ML/GenAI use cases and allows people to try and use models locally.
An Embedded Swift Matter application running on ESP32-C6
Run iOS apps without actually installing them!
The AI-ready design system for Korean digital government services.
Free and paid game assets and game resources for 2D games, 3D games, mobile games, Steam games, Unity games, and other games.
Pre-indexed code knowledge graph, auto syncs on code changes, for Claude Code, Codex, Gemini, Cursor, OpenCode, AntiGravity, Kiro, and Hermes Agent — fewer tokens, fewer tool calls, 100% local
🖥 Control your display's brightness & volume on your Mac as if it was a native Apple Display. Use Apple Keyboard keys or custom shortcuts. Shows the native macOS OSDs.
Korean persona dataset (NVIDIA Nemotron-Personas-Korea) → SQLite + FTS5 + MCP server for AI agents
Command-line tool that allows searching and downloading app packages (known as ipa files) from the iOS App Store
A Swift wrapper around libVLC for iOS, macOS, tvOS, visionOS, and Mac Catalyst
A modern port of Turbo Vision 2.0, the classical framework for text-based user interfaces. Now cross-platform and with Unicode support.
vLLM Metal plugin powered by mlx-swift — high-performance LLM inference on Apple Silicon
Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthr…
Reusable agent skills for Codex and compatible tools
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
Context window optimization for AI coding agents. Sandboxes tool output, 98% reduction. 15 platforms
Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-rep…
🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman
One CLAUDE.md file. Keeps Claude responses terse. Reduces output verbosity on heavy workflows. Drop-in, no code changes.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with C…
Surface AI blindspots before you ship. Put up to 8 AI models on every research, design or coding task.