Starred repositories
Open source inference engine that tunes its kernels on your hardware to find the fastest way to run each model. 2x faster than Ollama. Works on Apple Silicon, NVIDIA, AMD, Intel, or just a CPU.
Craft Anything: understand how any software works, and craft your own.
A modern terminal mail client for Gmail and Microsoft 365, with an MCP server for AI agents
Lightpanda: the headless browser designed for AI and automation
Unofficial Linux port of the Grok Bot desktop app
94 specialist Blender skills for Cursor, Claude Code, Kiro & Codex -> MCP-powered production pipeline from blockout to engine export.
Secure, fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in multi-language ruleset (N…
Your GeForce runs AI at half speed. This fixes it for 20/30/40 series cards. Up to 2× FP16 / BF16 / TF32 tensor throughput
CADCraft: computer-aided design and drafting — an open-source, clean-room CAD application in pure Rust
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing…
An experimental Rust port of the TypeScript 7 compiler (tsc)
Reverse engineer anything with agents, from app behavior down to native binaries.
Build and deploy iOS SwiftUI apps from Omarchy Linux on any PC (x86_64 or Apple Silicon), no Xcode required
DeepGEMM: clean and efficient BLAS kernel library on GPU
An image-to-world skillset for Claude.
An agentic skills framework & software development methodology that works.
A hierarchical inference engine for frontier MoE models: hot experts on the GPU (CUDA, Vulkan), warm ones in RAM, cold ones streamed from NVMe. Written in C, runs on the hardware you already own.
A decompilation of Super Smash Bros Melee brought to you by a bunch of clever folks.
A real browser inside your terminal