A hive mind communication platform

Community benchmarks and scripts for running Poolside Laguna S 2.1

Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Includes MLX Core macOS app with chat, agent mode, and tool calling.

A native Mac App for LLM fine-tuning on Apple Silicon — fully on-device, fully open source.

📊 LLM Context Benchmarks - A comprehensive benchmarking tool for testing LLMs with varying context sizes using Ollama. Features dual benchmark modes (API/CLI), automatic hardware detection (optimi…

Voxel sandbox game with a large render distance, procedurally generated content and some cool graphical effects.

SpaceXAI's coding agent harness and TUI. Fullscreen, mouse interactive, extensible.

SpaceXAI's coding agent harness and TUI. Fullscreen, mouse interactive, extensible.

Summarize videos via a yt-dlp → ffmpeg → whisper.cpp → AI pipeline

World of Warcraft Engine Experiment - a custom opensource client.

A collaborative list of awesome Zig libraries and resources.

The Xeneva Operating System

Based on openresponses repo, add validation for chat completions, and anthropic messages also.

macOS menu bar frontend for ds4.c (fine tuned DeepSeek V4 Pro/Flash) with 1M context.

Run DeepSeek V4 fully local: chat, a coding agent, and a design studio in one private desktop app.

DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm

3x decode TPS increase On Qwen 3.6 27B @ temp 0.6 | Native MTP Speculative Decoding On Apple Silicon With No External Drafter.

Swift API for MLX

LLMs and VLMs with MLX Swift

Krasis is a Hybrid LLM runtime which focuses on efficient running of larger models on consumer grade VRAM limited hardware

⚡ Native MLX Swift LLM inference server for Apple Silicon. OpenAI-compatible API, SSD streaming for 100B+ MoE models, TurboQuant KV cache compression, MACOS + iOS iPhone app.

Comprehensive status line plugin for Claude Code with context usage, API rate limits, and cost tracking

Object Oriented Framework to Work with C.

An implementation of the Jinja templating language in Zig.

AI-controlled visual design tool. LLM designs, humans view.

Agent Orcha is a declarative framework designed to build, manage, and scale multi-agent AI systems with ease. Use YAML to orchestrate complex workflows, manage diverse tools via MCP, and integrate …

A lightweight, user-friendly interface for managing a Caddy load balancer, packaged in a Docker container for easy deployment and configuration.