Explore the directory

A Model Context Protocol server that gives an AI coding agent access to Figma design data, so it can implement a UI from a Figma file more accurately than from a pasted screenshot.

• MCP servers
• Design tools

An open-source Python framework for building real-time voice and multimodal conversational AI agents, from a single voice assistant to a multi-agent system that hands off and coordinates work over a shared bus.

• Agent frameworks
• Speech

An offline, privacy-first English grammar checker written in Rust, built to lint documents in milliseconds with a small memory footprint and integrations for popular code editors.

• Editors

An open-source, MPP real-time analytics and search database that runs fast SQL queries, accelerates queries over lakehouse table formats, and combines structured, text and vector search in one SQL engine.

• Databases
• Data engineering

A Rust tensor library and deep learning framework that unifies training and inference in one codebase, JIT-compiling tensor operations with automatic kernel fusion across CUDA, ROCm, Metal, Vulkan and WebGPU.

• Models
• Inference

An MCP server that gives an AI assistant direct access to Xiaohongshu (RedNote), letting it log in, publish image or video posts, search content, read post details and comments, and post comments on the user's behalf.

• MCP servers

A lightweight, in-process vector database that embeds directly into an application for similarity search, combining dense and sparse vectors with full-text search and structured filters.

• Databases

A platform for generating and maintaining backend microservices, producing APIs, data models and DTOs from organization-defined templates that stay updated as packages change.

• Backend

A WebAssembly build of Postgres packaged as a TypeScript client library, letting an application run Postgres directly in the browser, Node.js, Bun, or Deno with no other dependencies to install.

• Databases

A Chinese-language knowledge base and hands-on guide to embodied AI, walking newcomers through a robot-manipulation project on the RoboTwin 2.0 simulation platform alongside an encyclopedia of the field's techniques.

• Tutorials
• Curated lists

A free, open-source machine translation API that runs entirely self-hosted, using the open-source Argos Translate library instead of proprietary services such as Google or Azure.

• APIs

A lightweight deep learning inference and training framework, used in production across more than 30 Alibaba apps, with companion projects for running large language and stable diffusion models locally on phones, PCs and IoT devices.

• Models
• Inference

A Turing-complete extension of Markdown that compiles a single document into books, academic papers, presentations, websites or knowledge bases, with functions, variables and a live preview.

• Documentation tools

A platform for automating software delivery: it builds, tests and ships code through a typed system API, with SDKs in eight languages and incremental, container-based execution.

• CI/CD
• Containers

A JavaScript library that runs Hugging Face Transformers models directly in the browser with no server, using an API similar to the Python Transformers library, for natural language, vision, audio and multimodal tasks.

• Inference
• Libraries

A library of agent skills that let an AI coding agent generate, inspect, source and slice CAD and robot-description files, from creating a part in STEP format to writing URDF robot structure files and checking manufacturability.

• Agent skills
• Design tools

An open-source TypeScript platform for building and deploying durable, long-running AI agents and background workflows, with retries, queues, scheduling and observability built in.

• Backend
• Workflow automation

A project-based course on building the environment, state management, verification and control mechanisms that make AI coding agent harnesses work reliably.

• Tutorials

A local proxy that lets OpenAI Codex, Claude Code, Claude Desktop and Grok Build run any large language model provider, translating between Codex's API format and more than 40 built-in providers or any OpenAI-compatible endpoint.

• LLM gateways

An open-source Model Context Protocol server that connects AI agents, IDEs and applications directly to databases such as PostgreSQL, MySQL, BigQuery, MongoDB and Spanner, with prebuilt tools and a framework for building custom, secured database tools.

• MCP servers
• Databases

A rich-text editor framework for React with AI features and shadcn/ui components, built around a headless plugin system for the underlying Slate editor.

• Libraries
• UI kits

A browser built for a person and their AI agents to use side by side, running agent browser tasks in isolated Spaces inside the same browser instead of a separate, bridged instance, so the agent can reach the user's real logins without taking over the browser.

• Browser automation

A single-file, serverless memory layer for AI agents that packages data, embeddings and search structures into one portable file, giving persistent, versioned, long-term memory without a database.

• Agent memory

A Gradio-based web interface for running the browser-use AI browser agent, adding support for many LLM providers, a persistent browser session, and the option to drive a user's own logged-in browser.

• Browser automation