Stars
Apple Silicon (MLX) port of Karpathy's autoresearch — autonomous AI research loops on Mac, no PyTorch required.
A user-friendly tool used to make wine wrapped ports of Windows software for macOS.
Place to keep various projects related to AI computing
A curriculum for learning about gpu performance engineering, from scratch to what the frontier AI labs do
AI-powered job search system built on Claude Code. 14 skill modes, Go dashboard, PDF generation, batch processing.
RTX 6000 Pro Wiki — Running Large LLMs (Qwen3.5-397B, Kimi-K2.5, GLM-5) on PCIe GPUs without NVLink
TurboMLX v0.1 Research Preview public source tree for Qwen3.5-focused MLX TurboQuant experiments.
A GPU-accelerated general-purpose metaheuristic framework for combinatorial optimization
A SOTA quantization algorithm for high-accuracy low-bit LLM inference, seamlessly optimized for CPU/XPU/CUDA, with multi-datatype support and full compatibility with vLLM, SGLang, and Transformers.
Context management for Claude Code. Hooks maintain state via ledgers and handoffs. MCP execution without context pollution. Agent orchestration with isolated context windows.
A dev agent multiplexer for git worktrees and coding agents.
A fast, lightweight, AMP ready WordPress theme built with speed and usability in mind.
🚀 The fast, Pythonic way to build MCP servers and clients.
pinksawtooth / GhidraMCP
Forked from LaurieWired/GhidraMCPIndependent fork of LaurieWired's GhidraMCP for continued development
AI-powered reverse engineering assistant that bridges IDA Pro with language models through MCP.
APOLLO: SGD-like Memory, AdamW-level Performance; MLSys'25 Oustanding Paper Honorable Mention
The simplest, fastest repository for training/finetuning medium-sized GPTs.
The ultimate training toolkit for finetuning diffusion models
TheTom / llama-cpp-turboquant
Forked from ggml-org/llama.cppLLM inference in C/C++
A reactive notebook for Python — run reproducible experiments, query with SQL, execute as a script, deploy as an app, and version with git. Stored as pure Python. All in a modern, AI-native editor.