op7418/CodePilot

A multi-model AI agent desktop client — connect any AI provider, extend with MCP & skills, control from your phone. Built with Electron + Next.js.

What it solves

CodePilot is a multi-model AI agent desktop client that provides a unified interface for interacting with various AI providers. It solves the problem of fragmented AI tools by allowing users to switch between different models and providers mid-conversation without losing context, while adding agentic capabilities like persistent memory, remote control, and extensible skills.

How it works

It operates as an Electron-based desktop application that connects to over 17 AI providers (including Anthropic, OpenRouter, Bedrock, Vertex AI, and local options like Ollama) via API. It integrates with the Model Context Protocol (MCP) and a custom skills marketplace to extend its functionality. For advanced system operations like file editing and terminal commands, it can optionally integrate with the Claude Code CLI.

Who it’s for

It is designed for developers and power users who want a centralized hub for their AI assistants, those who need to manage multiple AI models across different platforms, and users who want an AI agent that learns their preferences through a persistent workspace.

Highlights

  • Multi-provider Support: Connects to 17+ providers including cloud platforms, local LLMs, and custom OpenAI/Anthropic-compatible endpoints.
  • Assistant Workspace: Uses persona files (soul.md, user.md, etc.) and persistent memory to adapt to the user's workflow.
  • Remote Bridge: Allows remote control of the desktop agent via Telegram, Feishu, Discord, QQ, and WeChat.
  • Generative UI: Enables the AI to create interactive dashboards, charts, and visual widgets live in-app.
  • Session Management: Features split-screen dual sessions and the ability to rewind conversations to any checkpoint.
  • Extensibility: Supports MCP servers and reusable skills from the skills.sh marketplace.

Related

  • Project
    peterfei/ai-agent-team

    A virtual AI development team with specialized roles (PM, Backend, Frontend, etc.) and a persistent memory system for managing complex software projects.

  • Project
    AQBot-Desktop/AQBot

    A local-first desktop AI workbench that unifies multiple LLM providers, AI agents, knowledge bases, and MCP tools into a single, privacy-focused interface.

  • Project
    CopilotKit/open-multi-agent-canvas

    An open-source multi-agent chat interface that lets users manage multiple AI agents in one dynamic conversation using Next.js, LangGraph, and CopilotKit.

  • Project
    AIDotNet/OpenCowork

    OpenCowork is an open‑source desktop (Electron + .NET) platform that lets LLM‑based agents work directly on your local files, shell, and repositories. It supports multi‑agent teams, integrates with many chat services, offers five interaction modes (chat, clarify, cowork, code, acp), and provides a rich toolbox (file/shell access, browser automation, task/cron management, CodeGraph indexing, skill extensions). The same native .NET worker powers both the GUI and a terminal‑based CLI, keeping a single authoritative agent loop. Quick start requires Node ≥ 18 and .NET 11 SDK; builds are available for Windows, macOS, and Linux. Use cases include autonomous coding, scheduled ops, research/report generation, remote SSH tasks, and media‑pipeline design. Licensed under Apache 2.0.

  • Project
    AITabby/codexsplit

    A local control center for Codex Desktop that enables the integration of third-party AI models, official GPT account pooling, and intelligent agent routing.