boldsoftware/shelley

Shelley is a coding agent

What it solves

Shelley provides a mobile-friendly, web-based interface for a coding agent that allows users to interact with multiple models and modalities (like screenshots and charts) to write and manage code. It is designed to bring the agent directly to the compute environment, specifically tailored for use with exe.dev but usable elsewhere.

How it works

Shelley uses a Go backend with SQLite for storage and a TypeScript/Vue 3 frontend. It manages conversations consisting of messages from the user, the model, tools, and the harness. The UI is kept in sync with the backend via a Server-Sent Events (SSE) endpoint.

Who it’s for

Developers who want a web-based, multi-modal coding assistant that is accessible from mobile devices and can be integrated with their own authorization and sandboxing tools.

Highlights

  • Multi-modal support for screenshots, charts, and graphs.
  • Multi-model compatibility to leverage different AI innovations.
  • Mobile-friendly web interface to avoid terminal-based constraints.
  • Single-user architecture designed to bring the agent to the compute.

Related

  • Project
    shareAI-lab/Kode-CLI

    A terminal-based AI coding assistant that integrates codebase understanding, file editing, and command execution with support for multi-model collaboration and sub-agents.

  • Project
    anywhere-labs/Agents-Anywhere

    A remote control system that lets you manage and interact with AI coding agents (like Codex and Claude Code) running on your computer from a mobile device or web browser.

  • Project
    ConardLi/easy-agent

    Easy Agent is a terminal‑based, TypeScript‑written coding assistant that streams chat with Claude, OpenAI, Gemini, Ollama and other LLMs, lets the model read/write files, run shell commands, browse the web, and be extended via plugins and multi‑agent teams. It is at release‑candidate stage, awaiting npm publication.

  • Project
    QwenLM/qwen-code

    An open-source AI coding agent that provides a multi-protocol framework for automating development tasks across terminals, IDEs, and desktop apps.

  • Project
    aannoo/hcom

    A CLI tool that enables different AI coding agents to message, observe, and spawn each other across terminals to coordinate complex development workflows.