edge computing platform

This project is a comprehensive framework for building AI-powered applications, providing a unified toolkit for orchestrating language models, autonomous agents, and interactive user interfaces. It serves as a central library for managing the entire lifecycle of AI interactions, from initial prompt generation and model provider abstraction to complex, multi-step reasoning and tool execution. The framework distinguishes itself through its deep integration with frontend development, specifically by enabling generative user interfaces that render dynamic components directly from model outputs. I

workerd is a serverless edge runtime designed for executing lightweight, distributed functions at the network edge. It utilizes a V8-based JavaScript engine to provide fast startup and low memory overhead, while maintaining a WebAssembly-compatible execution environment that allows modules to run alongside JavaScript for high-performance computational tasks. The runtime supports isolate-based multi-tenancy to run multiple independent execution contexts within a single process. It implements an event-driven execution model that triggers code based on network requests or scheduled events and in

SvelteKit is a framework for full-stack web development that combines routing and server-side rendering to create websites with both client-side interactivity and server-side logic. It provides the infrastructure to build a variety of application types, including single page applications and static sites. The project utilizes an adapter-based deployment system to support multi-platform hosting. This allows a single codebase to be packaged for different environments, such as standalone Node servers, serverless edge deployments on Cloudflare, or hosted platforms like Vercel and Netlify. The fr

Nanobot is an orchestration framework designed for building, deploying, and managing autonomous AI agents. It provides a secure runtime environment that supports persistent memory, multi-step workflow management, and tool integration, allowing agents to maintain context and state across long-running tasks. The platform distinguishes itself through a unified model gateway that normalizes requests across diverse local and remote language models, alongside a multi-channel integration layer that connects agents to various messaging platforms. It enforces security through containerized sandboxing

This project is an edge computing development toolkit and serverless command line interface used to develop, test, and deploy serverless functions to a global edge network. It serves as an edge runtime bundler and resource orchestrator, managing the entire lifecycle of edge projects from local development to worldwide distribution. The toolkit distinguishes itself through distributed workflow management, coordinating stateful instances and the durable execution of long-running processes across the edge. It also provides specialized integrations for edge AI, including the management of vector

CoAI is an enterprise-grade, self-hostable AI gateway platform that unifies access to over 200 AI models from more than 35 providers through a single OpenAI-compatible API endpoint. It functions as a multi-tenant gateway, routing requests across providers with load balancing, automatic failover, and priority-based routing, while exposing standard OpenAI API endpoints for chat, image generation, model listing, and billing to enable seamless integration with existing tools and clients. The platform distinguishes itself through a comprehensive set of operational capabilities built around the gat

KoboldCPP is a local large language model inference engine and GGUF model runner designed to execute quantized models on personal hardware. It functions as a multimodal AI server and API gateway, providing OpenAI-compatible endpoints that allow third-party clients to interact with locally hosted models. The project distinguishes itself as an AI storytelling backend, featuring dedicated tools for long-form narrative management through persistent memory, world lore tracking, and character state management. It further extends its capabilities as a multimodal server capable of processing text, im

This repository is a collection of deployable project templates, reference architectures, and starter applications for building serverless web applications on Vercel. It serves as a library of implementation patterns and full stack starter kits designed to bootstrap new projects and reduce initial setup time. The collection provides a gallery of curated design patterns for frontend architecture and serverless application design. These reference architectures demonstrate best practices for structural design and the implementation of scalable web user interfaces. The repository covers a range

This project is a Model Context Protocol server and AI agent database connector. It provides a standardized communication layer that allows language models to interact with relational data stores, read database schemas, and manage PostgreSQL database resources. The implementation acts as a serverless host for the Model Context Protocol, deploying on distributed edge functions to connect AI assistants to a project. This enables AI agents to perform database administration, execute SQL queries, and handle schema migrations through an AI-compatible interface. The system covers broader capabilit

mistral.rs is an inference engine for large language models that runs locally and exposes models behind OpenAI and Anthropic-compatible APIs. It serves as a multi-model serving platform, capable of loading several models in a single server process with per-request routing and on-demand loading and unloading. The engine supports multimodal inference, processing text alongside images, video, audio, and speech inputs, and includes a quantized model deployment runtime that reduces memory use and speeds up inference on consumer hardware. The project distinguishes itself through an agentic tool exe

PartyKit is a serverless WebSocket backend platform for building real-time multiplayer applications. It provides a globally distributed edge computing runtime that runs stateful server code close to users, with automatic scaling and hibernation for idle rooms. The platform handles WebSocket connections, HTTP requests, and durable storage without requiring infrastructure management, and includes a client and server SDK with hooks, storage, and Yjs integration for building collaborative features. The platform distinguishes itself through per-room isolation using Durable Objects, where each uniq