A portable C99 inference engine that enables a 2.78-trillion-parameter model to run on a single CPU with as little as 8 GB of RAM by streaming weights from disk.

Context7 provides AI coding agents with up-to-date, version-specific library documentation and code examples to prevent API hallucinations and outdated code generation.

An optimized LLM inference server for Apple Silicon Macs featuring tiered KV caching, continuous batching, and a native macOS menu bar management app.

Official AI skills for GSAP that teach AI coding agents how to correctly use the GreenSock Animation Platform for web animations.

The open-source runtime for E2B, providing hardware-isolated Firecracker microVMs that allow AI agents to execute untrusted code with instant pause, resume, and fork capabilities.

An autonomous AI pentester for web applications and APIs that analyzes source code and executes real exploits to prove vulnerabilities before they reach production.

An AI red teaming platform that provides automated security scanning for AI infrastructure, agent skills, and LLM jailbreak evaluation to identify vulnerabilities and risks.

A Rust-based tool that enables AI agents to reliably control desktop applications using OS accessibility trees instead of visual pixel-guessing.

A platform for running multiple CLI-based AI coding agents in parallel across isolated git worktrees to eliminate context switching and speed up development.

A set of modular AI agent skills that implement a professional engineering workflow, moving project state from chat sessions into repository files for persistence and team collaboration.

A local AI search engine that automatically indexes folders to provide agents with precise code and document retrieval, reducing token costs and improving coding efficiency.

A comprehensive library of 388 modular agent skills and plugins for AI coding tools, providing specialized domain expertise across engineering, business, and research.

A collection of opinionated Oxlint rules for TypeScript and JavaScript that reject low-signal patterns and enforce stricter type safety and code efficiency.

A lightweight, native Discord desktop client written in Rust that significantly reduces RAM and CPU usage compared to the official Electron client.

A tool that converts websites and browser sessions into a CLI, enabling humans and AI agents to automate web interactions using logged-in Chrome profiles.

A virtualization project that enables running full macOS on M1/M2 iPads, allowing the use of pro apps like Xcode and Terminal.

A custom rustc backend that enables writing CUDA SIMT kernels in pure Rust, providing single-source compilation and a native Rust-to-PTX pipeline.

A CLI and library for evaluating and red-teaming LLM applications to replace trial-and-error prompt engineering with data-driven testing and security scanning.

An automated generator for Cloudflare WARP MASQUE configurations that runs on GitHub Actions or Cloudflare Workers, supporting proxy chaining to change exit countries.

An offline, mouse-themed file converter for Windows and macOS that supports images, documents, audio, and video using local engines like FFmpeg and LibreOffice.

A unified MCP server that integrates Google Ads, Meta Ads, and Google Analytics 4, allowing AI assistants to manage campaigns and analyze performance across all three platforms.

A highly optimized inference server for Qwen3.8-Flash-Next on AMD Strix Halo hardware, delivering significantly faster prefill and decode speeds via hardware-specific kernels.

A kernel extension for macOS 27 that spoofs the device region code from CH/A to LL/A to enable Apple Intelligence on mainland China Mac hardware.

A web browser that runs inside the terminal using the kitty graphics protocol, enabling developers and AI agents to interact with the web without leaving their command line.

A collection of packaged instructions and scripts that extend AI coding agents with specialized capabilities for Vercel deployment, performance auditing, and frontend engineering best practices.

An open-source product integration platform that provides a unified REST API syntax for connecting AI agents and backend services to multiple third-party apps.

A tool that integrates multiple AI agent harnesses like Claude Code and Pi into the Codex Desktop interface, allowing for cross-agent collaboration and remote execution.

A persistent memory server for AI coding agents that automatically captures and retrieves project context across sessions using hybrid search.

A cross-platform desktop management tool for OpenAI Codex that provides a visual interface for managing prompts, API providers, sessions, and MCP/Skills extensions.

A fly-connectome simulation that uses a biological neural network structure to trade cryptocurrency on Coinbase.

An orchestration layer for AI coding tools that adds an expert advisory board of 495 personas, a structured execution framework, and architecture verification gates.

A high-accuracy PDF parser that converts PDFs into structured Markdown or JSON for AI pipelines and automates the creation of Tagged PDFs for accessibility compliance.

A bilingual, step‑by‑step tutorial that teaches LLM inference fundamentals and guides you to build a minimal SGLang‑style inference engine, then deep‑dives into the real SGLang code and how to contribute to it.

DwarfStar (antirez/ds4) is a native inference engine for a few open‑weight LLMs (DeepSeek V4, GLM 5.x) that runs on consumer hardware (Apple Metal, NVIDIA CUDA, AMD ROCm). It supports SSD streaming, multi‑GPU and distributed tensor‑parallel execution, provides a CLI, an interactive coding‑agent, and an HTTP server, and includes tools for model download, evaluation, and benchmarking. The project is beta‑quality and builds on the llama.cpp/GGML ecosystem.

A distributed graph-based issue tracker and persistent memory system for AI agents, powered by Dolt for version-controlled task and dependency tracking.

An open-source AI memory platform that provides agents with persistent long-term memory using a self-hosted knowledge graph to store text, code, and session context.

An extremely fast Python package and project manager written in Rust that replaces pip, poetry, and pyenv to streamline dependency and version management.

A self-hosted AI gateway that provides a single entry point for managing multiple AI providers, API keys, and subscription accounts with built-in load balancing and usage tracking.

A framework for forward deployed engineers to manage client briefs, decisions, and delivery evidence for AI projects using AI coding agents and local Markdown records.

A macOS application that runs the Omarchy Arch Linux desktop as a hardware-accelerated, native app on Apple Silicon Macs using QEMU and Apple's Hypervisor Framework.

A skill for AI coding agents that visualizes project architecture and planned changes in an interactive HTML map to prevent scope mistakes and increase transparency.

A completion discipline for AI agents that uses runnable shell gates and evidence-backed ledgers to ensure substantial software work is fully completed and verified.

A multi-account switcher for Claude Code that prevents rate limits by automatically rotating between accounts based on usage quota.

A remote control system for AI agents that lets users dispatch tasks to agents running on their PC via a wearable voice-interface device and an iOS app.

A secure environment variable management system that provides AI agents with configuration schemas instead of secrets to prevent leaks.

An open-source alternative to Zapier that enables AI-powered workflow automation through a no-code builder and a TypeScript-based integration framework.

A drop-in proxy that automatically routes AI requests to the best available model from multiple providers using a local embedder rather than manual selection.

A model-aware long-context execution framework that reduces LLM serving latency and compute costs through head-aware KV reuse and sparse execution.