Explore the directory

A governance framework and set of documents that help organizations decide whether to allow a given MCP server, classify its risk and set the right controls before adopting it.

• MCP servers
• Security

An experimental port of NVIDIA's DLSS neural rendering and frame generation to Apple Silicon using MLX and Metal, plus a PyTorch backend for other GPUs, with a desktop app, web UI and command-line tool.

• Generative media

A modular agent framework built around triggers, decision-making and pluggable actions, letting developers compose an agent that reacts to inputs and executes operations without writing a fixed workflow.

• Agent frameworks

A browser-based platform for coordinating autonomous coding agents through a Kanban board, giving each task a planner, coder and QA agent plus a built-in terminal and code editor.

• Coding agents
• Agent frameworks

A TypeScript library that adds on-device text generation, speech-to-text and vision to Expo and React Native apps, using each platform's native AI models with no API keys or cloud calls.

• Inference
• Mobile

A Dart SDK that runs AI models directly on iPhones and Macs, covering chat, vision, speech-to-text, speech synthesis, image generation and retrieval, entirely offline.

• Inference
• Mobile

A local app that rents a GPU in your own Google Colab account and serves a large Qwen3.8 model on it, showing the cost before it starts and exposing the model to Codex or any OpenAI-compatible client.

• Inference
• Hosting

A single command-line tool that checks remaining quota, rate limits and cost across more than 16 AI coding assistant and LLM providers, instead of checking each provider's own dashboard.

• CLI tools
• Monitoring

A Chinese-language tutorial that builds an AI agent from scratch in plain Python, covering the agent loop, tools, memory and planning, before introducing frameworks such as LangChain, LangGraph and Dify.

• Tutorials

A collection of AI assistant skills that teach a coding agent how to install, configure, serve and troubleshoot vLLM-Omni, a framework for omni-modality model inference across text, image, video and audio.

• Agent skills
• Inference

A knowledge base of digital forensics investigation techniques, modeled on MITRE ATT&CK, cataloging each technique's objective, ways it can go wrong and mitigations for those weaknesses.

• Security

A survey and curated list of full-duplex spoken dialogue systems, the models and architectures that let a voice assistant listen and speak at the same time instead of taking strict conversational turns.

• Speech
• Papers

A set of self-contained Jupyter notebook tutorials introducing Hadoop, Spark and MapReduce, most runnable directly on Google Colab with no separate setup.

• Data engineering
• Tutorials

A modern, modular PHP framework built as a set of Composer packages, aiming to combine Laravel's developer experience with Symfony's discipline on PHP 8.5, including an MCP integration package.

• Web frameworks

A local memory and search layer that stores notes in SQLite and exposes full-text and vector-capable search over them through HTTP, MCP, a CLI and a web UI.

• Agent memory
• RAG

A collection of AI agent skills that automate recurring engineering workflows, such as fixing a changelog's version number before a commit, installable across more than 40 AI coding assistants.

• Agent skills

An open-weight, agent-oriented language model with 29 billion total parameters and 4 billion active per token, trained entirely on Ascend NPU hardware with a native 256K-token context window.

• Models

The source for the public website that documents the Weaviate vector database, built with the Docusaurus static site generator.

• Databases
• Documentation tools

An embeddable vector database with document storage, hybrid search, and metadata filtering, designed to scale beyond available memory without running as a separate server.

• Databases

An ebook that gives a practical, hands-on approach to building retrieval-augmented generation systems.

• RAG
• Books

A command-line toolkit for fine-tuning small language models with LoRA, quantizing them, and running them locally on CPU, designed for low-RAM laptops without a GPU.

• Models
• CLI tools

A spec-driven development toolkit for the Antigravity CLI that replaces raw conversational prompting with structured, compiled specifications for generating and executing coding tasks.

• Coding agents
• Agent skills

Sourcegraph's AI code assistant for Visual Studio, providing codebase-aware chat, multi-line autocomplete, a prompt library, and a choice of underlying models such as Claude, Gemini and GPT.

• Editors

A Claude Code plugin that brings other providers' models and coding tools, ChatGPT through Codex, Cursor, OpenCode Zen, Antigravity and Grok, into a single Claude Code session, each keeping its own login.

• Coding agents
• LLM gateways