Explore the directory

An on-screen aware desktop AI assistant that reads the content of the application currently on screen and answers questions about it without a screenshot.

• Agent frameworks

A curated list of project-based tutorials for learning to code by building applications from scratch, covering web, mobile, and game development plus machine learning.

• Tutorials
• Curated lists

A curated collection of agent skills for designers and builders, turning screen recordings, existing HTML pages, and full-page captures into reusable UI prompts.

• Agent skills
• Design tools

GitHub's AI coding assistant for Xcode, adding chat, inline completions, code review, and an agent mode that can edit files and run terminal commands.

• Coding agents
• Editors

A pixel-art desktop pet that reacts in real time to what an AI coding agent such as Claude Code or Codex is doing in the background.

• Coding agents
• Desktop utilities

A curated collection of Chinese-language ChatGPT prompts, with illustrated usage examples, covering programming, writing, image generation, and other tasks.

• Curated lists

A local-first AI agent workspace, sharing one runtime between a desktop GUI and a terminal TUI, for coding, writing, design, research, and automation.

• Coding agents

Open-source infrastructure connecting agent inference, feedback, and learning so an agent's model weights or its prompts, rules, and skills keep improving.

• Agent frameworks
• Models

An open-source, local-first desktop client for AI agents that brings chat, tool use, Skills, and Agent Client Protocol support into one Electron application.

• Inference

A hand-curated collection of papers, tools, models, benchmarks, courses, and communities covering prompt engineering and context engineering for large language models.

• Curated lists

A Python-embedded modeling language for convex optimization that lets a problem be expressed in natural mathematical form and solved with open-source solvers such as Clarabel, SCS, OSQP, and HiGHS.

• Libraries

A Python toolkit that intercepts every AI agent tool call, message, and delegation in application code to enforce policy, identity, and sandboxing before it happens.

• AI evals
• Security

A ranked list of popular GitHub repositories related to deep learning, ordered by their measure of community popularity and refreshed periodically.

• Curated lists

A Swift package of on-device inference frameworks for Apple platforms covering speech-to-text, speaker diarization, and text-to-speech.

• Speech

A portable microVM runtime for running AI agents in real virtual machines with their own kernel, embeddable in an app, checkpointable, and branchable into copy-on-write clones.

• Containers

An enterprise-class, open-source distributed monitoring platform that tracks the performance and availability of networks, servers, applications, and cloud infrastructure.

• Monitoring

An AI Agent Operating System that embeds a large language model into a kernel layer handling scheduling, memory, storage, and tool management for LLM agents.

• Agent frameworks

An open-source Tailwind CSS component library with prebuilt blocks, templates, and headless plugins for building websites and apps, plus a Figma design system and agent skills for theming.

• UI kits

An MCP server and CLI that gives an AI coding agent direct tools for building, running, and debugging iOS and macOS Xcode projects.

• MCP servers
• Mobile

A command-line tool, OpenAI-compatible server, and chat REPL that expose the language model already built into Apple Intelligence on Apple Silicon Macs.

• Inference
• CLI tools

An embedded operating system for Cortex-M and RISC-V microcontrollers that runs several mutually distrustful applications at once, isolating them with a Rust kernel and memory protection units.

• Libraries

An open-source framework from Google's Firebase team for building full-stack, agentic AI applications with SDKs for JavaScript, Go, Python, and Dart.

• Agent frameworks

A Claude Code, OpenCode, and Codex skill that runs an unattended modify, verify, keep-or-discard loop against a user-defined goal and a mechanical metric.

• Agent skills

A native Apple Silicon MLX runtime for Laya's typed decision models, answering short structured questions in single-digit milliseconds with no text generation.

• Inference