multi-runtime

EventMesh is a new generation serverless event middleware for building distributed event-driven applications.

A performant, declarative, and runtime-flexible web framework for Rust

Actor4j’s core implementation separates SDK and runtime, enabling flexible execution models.

Mecha SDK of Cloud Application Api. Let the code achieve "write once, run anywhere". With the help of the Capa project, your Java applications have the ability to run across clouds and hybrid clouds with small changes.

Multi-runtime DAG pipeline engine — declare in Python, execute in Go / Java / Python, decouple with JSON.

ADD — Agent Driven Development. Coordinated AI agent teams that ship verified software. Spec-driven TDD, trust-but-verify orchestration, maturity lifecycle. Runs on Claude Code + Codex CLI.

本地多运行时 Agent 工作台：围绕材料研究、生成可编辑报告、独立复核、追溯证据，并从人工反馈持续学习。

Recursive agents as skills for model harnesses

Omni is a governed cognitive runtime focused on observable reasoning, tool orchestration, safety boundaries, and multi-runtime AI execution.

Fix-until-green agent loop with shell-verify-as-truth, pluggable multi-runtime workers (Cursor/Cline/OpenCode/Codex/DSH/Pi), and fresh context per iteration.

Multi-runtime installer for the Ultra Builder Pro agent-engineering system — deploys commands, agents, skills, and hooks to Claude Code, OpenCode, Codex CLI, and Gemini CLI.

TypeScript application framework built around an explicit Application Graph for HTTP, tasks, queues, and triggers.

🚀 A modern, high-performance monorepo project designed for multiple runtime with hono. Node and cloudflare are supported!

An interactive playground for comparing LLMs and evaluating semantic routing pathways to optimize cost, speed, and token efficiency in real time.

The GitHub for AI Agents — open source, API-first, multi-runtime platform

Runly is a multi-runtime execution tool that runs the same codebase across different JavaScript environments for compatibility testing and validation.

Mission-centric runtime, debugging, and evaluation workbench for durable Missions across Codex, Qoder, and Claude Code.

Multi-runtime sandboxed code execution platform supporting Docker, Deno, Bun, Node.js, and Python via WebSocket and JSON-RPC 2.0 with layered security controls.

Composable multi-runtime agent application framework for deterministic capability assembly, controlled execution, and verifiable AI applications.

Knowledge Islands agentic harness — canonical home for Agent Skills, Agents, MCP servers, and Evals across the Knowledge Islands ecosystem.