Explore the directory

A local, browser-based review surface for AI coding agents that opens a plan, HTML artifact or code diff for markup, then sends the feedback straight back to the agent.

• Coding agents
• Code quality

A Claude Code plugin that turns a one-sentence project description into a custom multi-agent team and the skills those agents use, built for Claude Code's current workflow, persistent-agent and sub-agent delegation modes.

• Coding agents
• Agent skills

A cross-platform desktop app for organizing multiple AI chat sessions side by side, with prompt management, session isolation and a CLI controllable from coding agents.

• Inference

An enterprise agentic-workflow development platform that combines AI workflow orchestration, model management, MCP tool integration, RPA automation and team collaboration, released under a commercial-friendly license.

• Agent frameworks
• Workflow automation

A multi-agent framework for building autonomous agents that research, plan, code and execute tasks, with a five-layer stack covering prompts, context, tools, execution loop and deployment.

• Agent frameworks

An agent-orchestration plugin for OpenCode that routes tasks among seven specialized agents, running them as background jobs and mixing any models across providers.

• Coding agents
• Agent skills

A self-evolving engine for AI agents that uses a Genes-Capsules-Events model (GEP) to make an agent's learned skills and memory auditable as it evolves.

• Agent memory

A self-hosted AI research assistant that runs agentic, multi-step research across many LLMs and more than ten search engines, including private documents, with proper citations.

• Agent frameworks
• RAG

A Chinese-language beginner's tutorial for building applications with the LangChain framework, covering model calls, prompt management, document loaders, indexing and chains.

• Tutorials

An open-source status page and uptime-monitoring platform that treats monitors and pages as code, checked from many regions and operable from a CLI, Terraform, or an MCP server.

• Monitoring

An efficiency-oriented codebase for high-resolution image and video generation with a linear diffusion transformer, covering the SANA, SANA-Video, SANA-Sprint, SANA-WM and Sol-RL family of models with full training and inference pipelines.

• Models
• Generative media

A Go implementation of the Model Context Protocol, providing a high-level interface for building MCP servers with resources, tools and prompts.

• MCP servers

A curated list of embedded-programming resources, covering microcontroller programming, RTOS, bootloaders, Linux kernel and device-driver development, and embedded machine learning.

• Curated lists

A registry of design-engineering skills, reachable from a terminal CLI or over MCP, distilling UI lessons for AI coding agents to draw on.

• Agent skills
• Design tools

A hand-picked, multi-language directory of generative AI applications, organized into categories such as AI agents, coding assistants, content generation, data analysis and dozens of other use cases.

• Curated lists

An agent skill that audits a codebase with a capable model and writes self-contained implementation plans for cheaper models or other agents to execute.

• Agent skills

A general-purpose GitHub Action that runs Claude Code against pull requests and issues, answering questions, reviewing changes and implementing fixes when triggered by mentions, assignments or automation.

• Coding agents
• CI/CD

A review-first terminal diff viewer for agent-authored changesets, showing inline AI annotations beside the code in split, unified or responsive layouts.

• Terminals
• Code quality

A database for AI built on a storage format optimized for deep learning, storing and querying data, vectors and embeddings for LLM applications and managing datasets for model training.

• Databases

A lightweight, terminal-first AI-native development environment combining a GPU-accelerated terminal, code editor, file explorer and git-aware source control with an agentic AI side panel that can run local or hosted models.

• Editors
• Terminals

A high-accuracy retrieval-augmented-generation package for answering questions from scientific PDFs, text, Office documents and source code, with citations back to the source passages.

• RAG

A family of GUI agent models and systems from Tongyi Lab for automating desktop, mobile and browser interfaces, built on GUI-Owl foundation models with tool and MCP calling and long-horizon memory.

• Agent frameworks
• Models

An omni-modal generative system that understands mixed text, image, video and audio input and generates video with native stereo audio, distributed with nine bundled prompt-writing and video-generation skills for agent harnesses.

• Agent skills
• Generative media

A virtual filesystem backed by a Durable Object's SQLite state, giving an AI agent a pluggable execution surface: a sandboxed container, an isolated shell, or isolated JavaScript.

• Agent frameworks
• Containers