Local LLM Testing & Benchmarking for Apple Silicon

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

Open-source framework for superagents.

Visualizer for neural network, deep learning and machine learning models

258 KB WASM runtime for Needle a 26M-parameter tool-calling transformer. Runs in browser, Cloudflare Workers, and Node.js. No backend required.

26m function call model that runs on incredibly small devices

The bastard son between Cursor and Obsidian

LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar

Very low latency speech to text, intent recognition, and text to speech, for building voice agents and interfaces

Open source repository of plugins primarily intended for knowledge workers to use in Claude Cowork

EdegQuake 🌋 High-performance GraphRAG inspired from LightRag written in Rust; Transform documents into intelligent knowledge graphs for superior retrieval and generation

A complete GPT language model (training and inference) in ~600 lines of pure C#, zero dependencies

✨ Light and Fast AI Assistant. Support: Web | iOS | MacOS | Android | Linux | Windows

Strix Halo Installation notes and container Dockerfiles

Interactive launcher and benchmarking harness for llama.cpp server throughput, with tests, sweeps, and round‑robin load tools.

A user-friendly GUI for llama.cpp — convert, quantize, and run GGUF models without touching the terminal.

Fine-tune and run LLMs locally on your M-series Mac. A powerful desktop interface built on Apple's MLX framework for zero-setup AI.

Extract and convert data from any document, images, pdfs, word doc, ppt or URL into multiple formats (Markdown, JSON, CSV, HTML) with intelligent structured data extraction and advanced OCR.

A modern desktop application for exploring, managing, and analyzing vector databases

Comprehensive resource on Generative AI security — prompt injection, jailbreaking, RAG security, red teaming, guardrails, and more. One folder per topic.

Ontology, and Knowledge graph based RAG that uses local LLM.

Public roadmap for Inferencer. Ideas, feature requests, and bug reports are all welcome.

Local modular AI assistant with speech, vision, and robotics support. Uses Qwen3-VL-4B in LM Studio.

Docker configuration for running VLLM on dual DGX Sparks

A C#/.NET library to run LLM (🦙LLaMA/LLaVA) on your local device efficiently.