Explore the directory

A set of Agent Skills that carry a change from a vague idea through scoping, architecture, development, review, testing, and documentation, with state kept in files rather than a chat session.

• Agent skills

An end-to-end platform for building computer vision models, from dataset preparation and training through optimization and deployment, tuned for Intel's CPU, GPU, and other accelerator hardware.

• Models

A Codex skill that turns articles, course notes or outlines into a set of Chinese hand-drawn technical explainer images, delivered as full-page PNGs rather than an editable slide deck.

• Agent skills
• Generative media

An open-source in-memory data grid that stores and distributes key/value data across elastically scalable clusters for high availability and fault tolerance.

• Databases

The official Python client and SDK for the Qdrant vector search engine, with type definitions for the full API, synchronous and asynchronous requests, and a local mode that runs without a server.

• Databases

A standalone, open-source MCP host that combines MCP servers with a language model to present agent experiences such as chat, and can be deployed or embedded into other applications.

• Agent frameworks
• MCP servers

A daemon that bridges Feishu/Lark to AI coding CLIs such as Claude Code, Codex, and Gemini, spawning a separate live-streaming CLI session for every direct message, group, or topic.

• Coding agents

A tool that compiles LLM-driven research into structured knowledge bases for any AI agent, capturing rough ideas, running parallel research, and promoting approved briefs into delivery projects.

• Agent memory

An open-source, self-hostable shared workspace where people and AI agents such as Claude Code, Cursor, or Codex work together in pods, each agent keeping its own memory, skills, and workstation.

• Coding agents
• Agent frameworks

An image and video management app for AI-generated media that reads generation metadata from tools such as Stable Diffusion web UI, ComfyUI, Fooocus, and NovelAI, with fast thumbnails, tag search, and semantic search.

• Generative media

A tool that coordinates several AI coding CLIs, such as Claude Code, Codex, and Kiro, in isolated tmux sessions so a supervisor agent can delegate work to specialist agents in parallel or in sequence.

• Coding agents
• Agent frameworks

A command-line tool that runs a Node.js application locally the way AWS Lambda would, and packages or deploys it to Lambda.

• Hosting

A desktop IDE for running AI coding agents such as Claude Code, Codex CLI, and Gemini CLI, with a project dashboard, kanban board, multi-session management, and cost tracking.

• Coding agents

A research framework covering the full lifecycle of GUI agents: online reinforcement-learning training, standardized evaluation across benchmarks, and deployment to control real mobile devices by natural language.

• Agent frameworks
• Models

Alibaba's high-performance inference engine for large language models, used internally across Alibaba's businesses, with CUDA kernel optimizations, quantization, LoRA serving, and multi-GPU tensor parallelism.

• Inference

A self-hosted cloud platform that packages a Kubernetes cluster, an app store, GPU-backed local AI models and cloud development environments into a single downloadable binary.

• Containers
• Hosting

A code-first TypeScript toolkit for building, evaluating, and deploying AI agents, from single tasks to multi-agent systems, with full type safety and support for Node.js and browser runtimes.

• Agent frameworks

A Java enterprise backend and management platform for Xiaozhi ESP32 smart-hardware devices, handling device monitoring, voice pipelines and conversation records.

• Backend

A Codex plugin that lets an AI agent draw scientific figures live inside the visible draw.io desktop canvas, calling draw.io's own graph API through a local MCP server rather than automating the mouse and keyboard.

• MCP servers
• Design tools

A Streamlit-based graphical interface for building and running CrewAI agents and tasks without writing code, supporting Conda or virtual-environment installs on Windows, Linux, and macOS.

• Agent frameworks

A curated list of research papers, workshops, and tools on retrieval-augmented generation for large language models, organized by topic from embeddings to evaluation.

• RAG
• Papers

An end-to-end autonomous research agent that carries a research idea through literature search, experiment design, real GPU training, result analysis, and a complete LaTeX paper with figures drawn from actual experiment data.

• Agent frameworks
• Models

An agent framework in which every side effect an agent performs runs through the runtime as a recorded host call, so any run can be checkpointed, replayed with zero LLM calls, and resumed after a crash.

• Agent frameworks

A distributed inference engine that lets you build your own AI cluster across ordinary machines to serve large language models, with pipeline-parallel sharding and GPU or Mac backends.

• Inference