Projects sharing features with Edge Runtime

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

Rivet is a distributed infrastructure for managing the lifecycle, addressing, and persistence of stateful actors and durable execution engines. It provides a distributed process sandbox that executes application logic within lightweight isolates, ensuring resource isolation and fast cold starts. The system is designed to coordinate multi-step operations using persistent queues and timers to guarantee reliable task completion across distributed environments. The platform specifically enables the orchestration of stateful AI agents that maintain persistent memory and state across long-running i

Vercel is a cloud platform for building, deploying, and scaling web applications. It provides a unified infrastructure that automates the build process by detecting project frameworks and distributing static and dynamic content through a global content delivery network. The platform executes application logic using serverless functions that scale automatically based on real-time traffic demand. The platform distinguishes itself through a centralized AI gateway that proxies requests to multiple model providers, enabling standardized authentication, observability, and cost tracking. It supports

Wasmer is a high-performance runtime engine designed to execute sandboxed WebAssembly modules across server-side, edge, and browser environments. It functions as a comprehensive platform for building, distributing, and running isolated applications, providing a secure and portable execution layer that maintains consistency across diverse hardware architectures and operating systems. The platform distinguishes itself through a robust toolchain that enables cross-language interoperability and the transformation of code into portable binary packages. It supports ahead-of-time binary generation t

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

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

This project is a disposable email inbox service built to run entirely on Cloudflare's edge network. It creates temporary email addresses that automatically receive and store incoming messages and attachments, all without managing any traditional server infrastructure. The service uses Cloudflare Workers for serverless processing, Durable Objects for persistent inbox state, and Workers KV for storing email data, with attachments handled through R2 object storage. The service distinguishes itself through a comprehensive set of access and management features. Users can authenticate through mult

Microfeed is a serverless content management system hosted on Cloudflare infrastructure for managing blogs, podcasts, and multimedia feeds. It functions as a self-hosted multimedia publisher and a headless content API, allowing users to organize text, audio, and video content under a custom domain. The system includes an RSS and JSON feed generator to distribute machine-readable content to external aggregators and podcast players. It provides a programmatic interface for managing and serving content as a data source for external client applications. The platform covers administrative dashboa

E2B is a cloud-based infrastructure platform designed to provide secure, isolated execution environments for code and shell commands. It functions as an ephemeral orchestrator that provisions lightweight virtual machines, allowing developers and autonomous agents to run untrusted processes within a sandbox that is completely separated from the host system. The platform distinguishes itself through its focus on programmable, serverless workspaces that support the full lifecycle of cloud-based development. By utilizing hardware-level isolation and snapshot-based resumption, it enables the near-

Daytona is a cloud-native development environment platform designed to orchestrate ephemeral, containerized workspaces. It provides a centralized system for managing reproducible coding environments as code, ensuring consistency across distributed teams by abstracting the underlying infrastructure. By utilizing declarative configuration, the platform automates the entire lifecycle of development sandboxes, from initial provisioning to resource governance. The platform distinguishes itself through its infrastructure-agnostic runner layer, which allows development environments to be deployed ac

Elysia is a high-performance TypeScript web framework designed for building type-safe backend services. It provides a modular, plugin-based architecture that allows developers to compose server logic, middleware, and validation schemas into scalable application instances. By leveraging native web standards, the framework ensures portability across diverse JavaScript runtimes, including Node.js, Deno, and various edge computing environments. The framework distinguishes itself through its focus on end-to-end type safety, automatically synchronizing request and response definitions between the s

Sandbox Agent is a platform designed to manage, secure, and orchestrate autonomous coding assistants. It provides a standardized infrastructure for executing untrusted code and managing agent lifecycles within isolated, containerized environments. By decoupling agent execution from client connections, the platform ensures that session states remain persistent across process restarts and network interruptions. The project distinguishes itself through a capability-based security model that enforces granular permission checks on tool usage, ensuring that autonomous processes operate within defin

Scriptcat is a user script manager and browser extension designed to install, execute, and manage custom JavaScript scripts to modify website behavior and extend browser functionality. It features a JavaScript sandbox environment that provides specialized APIs for storage, cookies, and system notifications, alongside a cloud-synced script repository to keep subscriptions and configurations consistent across multiple devices. The project includes an in-browser script editor for writing, testing, and debugging code directly within the browser. It also incorporates a cross-domain request engine

Bubblewrap is an unprivileged sandbox execution utility for Linux that isolates processes from the host system. It creates secure environments by leveraging Linux namespaces to separate system resources, including network, PID, and IPC stacks. The project distinguishes itself by enabling the execution of untrusted software without requiring root privileges on the host machine. It prevents privilege escalation by disabling the execution of setuid binaries and uses user identity mapping to isolate process permissions from the host operating system. The tool manages a comprehensive security sur

Pandas AI is a data analysis library and natural language interface that uses large language models to perform conversational querying on structured datasets. It functions as a retrieval-augmented generation framework designed to translate plain text questions into executable code for extracting insights from dataframes and structured files. The system includes a dedicated sandbox execution environment that runs AI-generated analysis code within an isolated container to prevent security risks and system compromise. It employs a natural language translation layer and contextual retrieval to ma

CodeWhale is an AI coding agent orchestrator and development harness designed to coordinate autonomous agents that read, edit, and verify code. It provides a secure environment for AI agents to perform multi-step software engineering tasks, utilizing a sandboxed execution model to isolate shell commands and protect the host system. The system distinguishes itself by spawning multiple independent agents in parallel to handle separate investigation or implementation slices simultaneously. It employs a multi-model gateway to route requests across various cloud APIs and local servers, and utilize

Moltworker is an AI agent sandbox and model orchestrator designed for the secure execution of untrusted code and shell commands generated by large language models. It functions as a gateway proxy that routes requests to multiple AI providers through a unified interface, integrating a container runtime backed by S3-compatible object storage to persist state across ephemeral lifecycles. The system distinguishes itself by combining an AI model orchestrator with a headless browser controller for automated web scraping and screenshot capture. It manages the full lifecycle of AI agents, including m

Open-SWE is an asynchronous software engineering agent and orchestrator designed to automate end-to-end coding tasks and pull request reviews. It functions as a middleware framework that coordinates long-running AI operations across multiple subagents, utilizing state persistence and human-in-the-loop oversight to manage complex workflows. The system is distinguished by its use of isolated remote Linux sandboxes for secure code execution and shell command processing. It features a webhook-driven integration platform that triggers automated engineering tasks via mentions and events in GitHub,

LiveContainer is an iOS app container manager that runs applications in isolated sandboxes with separate data, keychain, and vendor identifiers, bypassing Apple's free developer account installation limits. It uses Just-In-Time compilation to launch unsigned apps without a developer certificate, and supports running multiple instances and versions of the same app simultaneously. The tool also injects custom dynamic libraries and framework tweaks at launch, applied globally or per application. Beyond basic containerization, LiveContainer provides advanced multitasking with resizable virtual or

Deobfuscator is a static analysis and manipulation framework designed to inspect and modify compiled Java class files and bytecode instructions. It functions as a deobfuscator that simplifies and reverses obfuscated Java applications, alongside operating as a security runtime environment that isolates and executes untrusted or potentially malicious Java bytecode safely. The project processes class files through a sequence of custom transformation passes using visitor-based instruction parsing and a static class analysis engine that maps out class hierarchies and cross-references without dynam

rusty_v8 is a Rust wrapper for the V8 JavaScript engine that allows for the embedding of a JavaScript runtime into native applications. It provides core components for managing engine bindings, memory allocation, sandboxed isolates, and the execution of WebAssembly modules. The project features a native host function bridge to map Rust functions to JavaScript objects and a dedicated memory allocator to manage thread-safe allocation and heap pressure. It includes a system for compiling and executing binary WebAssembly modules within the hosted native environment. The runtime covers capabiliti

Microsandbox is a microVM sandbox runtime and hardware-isolated code executor designed for running untrusted code. It functions as an embedded virtual machine manager that allows applications to spawn and control lightweight virtual machines directly within code without the need for a background daemon. The system provides a secure execution environment for AI agents by exposing server controls that allow them to execute tools and manage files. It utilizes standard container image formats and volume workflows to initialize guest virtual machines and implements a secret management mechanism th

OpenFang is an operating system for LLM agents designed to orchestrate autonomous agents with built-in task scheduling, tool sandboxing, and multi-model routing. It provides a secure AI execution environment that integrates prompt injection scanning, cryptographic audit trails, and resource metering to ensure controlled processing. The platform distinguishes itself through a comprehensive security architecture, featuring fuel-metered tool sandboxing and an immutable activity audit trail based on cryptographic hash-chains. It implements high-assurance identity verification via signed manifests

CubeSandbox is a Kubernetes-based platform for executing AI agents in secure, lightweight environments. It provides a code execution sandbox that uses hardware isolation and dedicated guest kernels to run untrusted code without risking the host system. The project features a network egress firewall that restricts outbound communication via domain allowlists and audit logging. It also includes a container snapshotting manager capable of capturing the runtime memory and disk state of environments to enable instant cloning and recovery. The platform covers cluster orchestration through a web-ba

rllm is an asynchronous reinforcement learning framework for training language agents. It provides a unified pipeline that runs the same agent code for both evaluation and training, automatically capturing traces for gradient computation. The framework supports distributed reinforcement learning across multiple GPUs and nodes using pluggable backends, and executes agents in isolated sandboxes—either locally or in the cloud—for safe and scalable rollout collection. It trains agents built with LangGraph, SmolAgents, OpenAI Agents SDK, or custom frameworks without requiring core logic changes. T

OpenHuman is an AI application framework for building private intelligence systems and personal AI layers. It provides a system for deploying private AI assistants that execute technical tasks and manage personal knowledge bases. The project features a model-agnostic request proxy that routes AI workloads to different large language models based on requirements for reasoning, speed, or vision. It integrates an OAuth-driven data integrator to synchronize personal information from external services into a local knowledge base composed of hierarchical Markdown summaries. The framework also inclu