stagewise-io/stagewise

The Open Source Agentic IDE. Create and orchestrate coding agents, show app previews and run git workflows. Use your favorite models across all providers.

What it solves

stagewise is an agentic IDE designed to eliminate context switching for developers. It integrates a coding agent directly into the development environment, allowing users to build and browse simultaneously while leveraging AI to modify code and reverse-engineer websites.

How it works

The tool functions as a combined browser and editor. The built-in coding agent has full access to the browser's console and debugger, enabling it to diagnose and fix issues in real-time. Users can make temporary test changes or connect a local codebase for permanent edits. It also supports "Bring Your Own Key" (BYOK) for various AI providers (including local inference) or a managed stagewise account to access a wide range of open-weight and proprietary models.

Who it’s for

Web developers who want an AI-powered workflow that integrates browsing, debugging, and coding in one tool, and those who prefer flexibility in which LLM provider they use.

Highlights

  • Integrated Agentic Workflow: A coding agent with direct access to the browser console and debugger.
  • Browser-IDE Hybrid: Ability to browse and build in the same tool to reduce context switching.
  • Website Reverse-Engineering: Tools to analyze and reverse-engineer components, style systems, and color palettes of any website.
  • Model Flexibility: Support for a vast array of models via BYOK (OpenRouter, Mistral, Moonshot AI, etc.) or a managed subscription.
  • IDE Integration: Ability to view and apply code changes in a preferred external editor.

Related

  • Project
    get-bb/bb

    bb is an agent‑driven IDE that can control, customise, and automate itself via desktop, web, CLI, and HTTP API surfaces. It runs tasks in live threads, supports plugins, and ships as a native desktop app (macOS stable, Linux/Windows experimental) or via `npx bb-app`. Production usage sends anonymous telemetry; development mode does not. The project is actively developed with a stable core but evolving workflows.

  • Project
    browserbase/skills

    A collection of skills for Claude Code that enable AI agents to perform browser automation, UI testing, and deep web research via Browserbase.

  • Project
    zai-org/ZCode

    ZCode is a multi-platform AI programming workbench that provides a unified interface for AI agents across desktop, web, and terminal environments, supporting local and remote development workflows.

  • Project
    cloudflare/vibesdk

    An agentic platform for building and deploying full-stack applications on Cloudflare, featuring an AI coding agent that handles planning, file editing, and live previews.

  • Project
    ConardLi/easy-agent

    Easy Agent is a terminal‑based AI coding assistant that can read, edit, and run code under configurable permission rules and optional OS sandboxing. It supports major LLM providers, offers persistent sessions, extensibility via plugins/skills, and multiple safety modes (plan, auto, default). Install via npm, trust a workspace, then interact with the REPL to ask questions, make multi‑file changes, run tests, and undo actions.