-
Silent Tide Software
- ¯\_( ͡❛ ͜ʖ ͡❛)_/¯
- https://store.steampowered.com/app/4094850/Echoes_of_the_Cove/
- https://echoesofthecove.com
- https://ai.google.dev/competition/projects/the-intellect-hub
Stars
A dark, rounded-card layout for Herdr that combines the bright text and vivid terminal colors of dtellz-dark with the separated panel design of Islands by Cody Packer
A dark theme for Herdr with nearly black terminals, a charcoal interface, pure white main text, and vivid ANSI color
Extensions for pi, the terminal-based coding agent
Valve's official ARM64 SteamOS in a lightweight VM on Apple Silicon: libkrun + Venus + MoltenVK, controllers, CoreAudio sound
learn LLM inference system on Apple Silicon for systems engineers: build a tiny vLLM + Qwen
A complete World of Warcraft 1.12.1 client, written from scratch in Rust and Bevy
Privacy-focused macOS tool to block Apple Private Cloud Compute while preserving local on-device AI
MCP server to find and apply to tech jobs in Spain with your AI agent: job search, remote jobs, companies, salaries, auto apply. MCP para buscar trabajo y empleo tech en España: ofertas en remoto, …
A modern replacement for Redis and Memcached
A small int8 RNN trained from scratch on the Three.js source using EGGROLL (gradient-free Evolution Strategies). Testing whether concentrated domain capacity beats a generalist LLM on narrow code-g…
SpeederX / siliang-engine
Forked from ggml-org/llama.cppSiliang Engine is an experimental inference engine based on llama.cpp specifically optimized for MoE LLMs
Cross-platform, graphics API agnostic, "Bring Your Own Engine/Framework" style rendering library.
A minimal autonomous code-agent CLI built with Qwen Code
LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar
Offline AI chat between iPhone and MacBook. Local LLM served peer-to-peer over Multipeer Connectivity. No internet, no router, no cloud. Everything but your imagination stays on-device.
Instant, Concurrent, Secure & Lightweight Sandbox for AI Agents.
HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.
MLX Local voice generation pipeline for Apple Silicon, using the "Text-Acoustic Dual Alignment" model from HumeAI
This repository contains the code to train and evaluate TRIBE v2, a multimodal model for brain response prediction