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 numerous 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 and remote control.

How it works

The application is built as an Electron desktop app that connects to over 17 AI providers via API (including Anthropic, OpenRouter, Google Vertex AI, and local options like Ollama). It implements the Model Context Protocol (MCP) and a custom skills system to extend its functionality. It also features a "Remote Bridge" that connects to messaging platforms like Telegram and Discord to allow remote control of the AI assistant from a phone.

Who it’s for

It is designed for developers and power users who want a single, powerful hub for their AI workflows, those who need to integrate multiple AI models, and users who want an AI assistant that learns their preferences through a dedicated workspace.

Highlights

  • Multi-provider support: Connects to 17+ providers including cloud platforms, local self-hosted models, and custom OpenAI/Anthropic-compatible endpoints.
  • Assistant Workspace: Uses persona files (soul.md, user.md, etc.) and persistent memory to adapt to the user over time.
  • Remote Bridge: Enables interaction with the desktop AI agent via Telegram, Feishu, Discord, QQ, and WeChat.
  • Generative UI: AI can create interactive dashboards, charts, and visual widgets rendered live in-app.
  • MCP & Skills: Supports MCP servers and a marketplace for reusable skills.
  • Session Management: Ability to pause, resume, and rewind sessions to specific checkpoints.
  • Task Scheduler: Schedule recurring AI tasks using cron expressions.

Related

  • Project
    formulahendry/wechat-acp

    A bridge that connects WeChat direct messages to ACP-compatible AI agents, allowing users to interact with local AI CLI tools via WeChat.

  • 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
    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
    uvwt/agentdock

    AgentDock is an open‑source runtime that lets LLM chat agents (e.g., ChatGPT) safely perform file operations, run commands, use Git, automate browsers, and coordinate work across multiple computers or containers via a secure HTTP‑based MCP endpoint. It provides fine‑grained permission controls, task persistence, and extensible Skills, but does not include its own chat UI or model inference.

  • Project
    im4codes/imcodes

    A messaging and memory layer for coding agents that enables remote machine control, shared context across AI providers, and supervised delivery pipelines.