The headless browser for AI agents and web scraping

A self-improving RLM agent for coding workflows and long-running autonomous tasks.

Snapshotable JavaScript runtime via WebAssembly. Runs QuickJS-NG compiled to WASM with the ability to snapshot the entire VM state — including pending promises — and restore it in a fresh instance.

Own your compute, own your intelligence. Time to build your Personal AI Data Center.

A high-throughput and memory-efficient inference and serving engine for LLMs

An agentic system that auto-optimizes LLM workloads on AMD GPUs.

Official AMD catalog of AI agent skills. Empower your AI agents with AMD's optimized SW stack.

Sub2API 一站式开源中转服务，让 Claude、Openai 、Gemini、Grok订阅统一接入，支持拼车共享，更高效分摊成本，原生工具无缝使用。

Un-nerfed Claude Code system prompts — a drop-in replacement set that flips the stock "be brief / minimal / concise" directives into "be thorough / complete / senior-engineer-grade," applied via tw…

⚙️🦀 Build modular and scalable LLM Applications in Rust

The AI agent sandbox runtime. Boot any OCI image as a Firecracker microVM, Linux container, or Apple Silicon VM in ~400 ms — zero-copy DAG storage, P2P image sync, native MCP for opencode/Claude Co…

High-performance FlashAttention-2 for AMD, Intel, and Apple GPUs. Drop-in replacement for PyTorch SDPA. Triton backend for ROCm (MI300X, RDNA3), Vulkan backend for consumer GPUs. No CUDA required.

ROCmfp4

Build continually improving models on your agent traces by distilling frontier open models

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills

A consolidated RDNA3/Zen3 reference for architecture, ISA, and ML training on consumer Radeon hardware (RX 7700 XT).

FlashAttention-2 Triton kernel for AMD RDNA3 (gfx1100 / Radeon RX 7900 XT/XTX/GRE): forward, backward, and split-K decode

This is a rocm version flash attention forked from flash_attention, with full modifed ck backend to realize full support for the RDNA3 architecture AMD Graphic Card.

WebTorrent, the streaming torrent client. For the command line.

PyTorch bindings of GGML operators with autograd

Rust GUI components for building fantastic cross-platform desktop application by using GPUI.

A native TypeScript/JavaScript compiler written in Rust. Compiles TypeScript/JavaScript directly to executables using SWC and LLVM.

The AI SDK for your iOS and macOS Apps

Pi extension for OpenCode-style MCP client support

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

Skills for Designers and Engineers.

Apple liquid glass for React — pure SVG filters, no WebGL, no canvas. SSR-ready, ~2 KB gzip.

Toolkit for building native desktop apps