[opensourcedex]

Dive is a free, open source ai interaction & interfaces project written in TypeScript and released under MIT. It has 1,827 GitHub stars, 175 forks and 34 open issues, and was last pushed 2 months ago. On this registry it ranks #64 of 76 tracked projects in AI Interaction & Interfaces, with 5 head-to-head comparisons available.

What is Dive?

What it is

Dive is an open-source desktop application that acts as a Model Context Protocol host for large language models that support function calling. It lives in the AI and machine learning ecosystem for AI interaction interfaces, and it is a TypeScript project under the MIT license. It connects users to ChatGPT, Anthropic, Ollama, and OpenAI-compatible models while supporting MCP servers through stdio and SSE modes.

The problem Dive addresses is the difficulty of configuring a chat interface, model provider, API keys, MCP servers, and tool permissions together. It provides a desktop client that can switch models, manage API keys through model_settings.json, enable or disable MCP tools, and access managed MCP servers through OAP Cloud.

Key capabilities

  • Dive supports ChatGPT, Anthropic, Ollama, and OpenAI-compatible models, so users can connect one desktop chat workflow to multiple providers.
  • It integrates with MCP servers in stdio and SSE modes, allowing local servers or server-sent-event endpoints to be used.
  • OAP Cloud integration gives one-click access to managed MCP servers through OAPHub.ai, reducing complex local deployment.
  • API management supports multiple keys and model switching through model_settings.json, and tool control lets users enable or disable individual MCP tools.
  • Built-in local tools include Fetch, File Manager, and Bash, which provide web requests, file reading and writing, and command execution.
  • The application includes an MCP Server Installer Agent, multiple elicitation support, @ file path search, chat draft saving, keyboard shortcuts, auto-update checks, skills, slash commands, and chat history search.

Who uses it and how

  • Desktop users on Windows, macOS, and Linux can install Dive as a chat client for local Ollama models or remote OpenAI-compatible models.
  • Developers can use Dive to test stdio and SSE MCP servers, choose active tools, and send requests to the model with those tools available.
  • Teams can use OAP Cloud through OAPHub.ai for managed MCP servers while keeping a desktop chat workflow.
  • Users can rely on Fetch, File Manager, and Bash for file and command workflows, and use the installer agent to configure additional MCP servers.

Getting started

Users download the latest release from the GitHub releases page and choose the Windows Tauri or Electron build, the macOS Electron .dmg build, or the Linux build. On Windows, Python and Node.js environments are downloaded automatically after launching, and OAP Cloud access is available through OAPHub.ai.

When to use it — and when not to

Dive is useful when you want a desktop MCP host that connects local or remote LLMs to MCP tools and managed cloud servers without building your own interface. It is less suitable if you need stable MCP server authentication, because the README states that this feature is currently unstable and may require frequent re-authorization. It is also not ideal if you specifically need a macOS Tauri build, since the platform table lists that build as upcoming.

project readme (upstream, from github) — read inline

Dive AI Agent

GitHub stars GitHub forks GitHub watchers GitHub repo size GitHub language count GitHub top language GitHub last commit Discord Twitter Follow

Dive is an open-source MCP Host Desktop Application that seamlessly integrates with any LLMs supporting function calling capabilities. ✨

Dive Demo

Features 🎯

  • 🌐 Universal LLM Support: Compatible with ChatGPT, Anthropic, Ollama and OpenAI-compatible models
  • 💻 Cross-Platform: Available for Windows, MacOS, and Linux
  • 🔄 Model Context Protocol: Enabling seamless MCP AI agent integration on both stdio and SSE mode
  • ☁️ OAP Cloud Integration: One-click access to managed MCP servers via OAPHub.ai - eliminates complex local deployments
  • 🏗️ Dual Architecture: Modern Tauri version alongside traditional Electron version for optimal performance
  • 🌍 Multi-Language Support: Supports 24+ languages including English, Traditional Chinese, Simplified Chinese, Spanish, Japanese, Korean, German, French, Italian, Portuguese, Russian, Thai, Vietnamese, Filipino, Indonesian, Polish, Turkish, Ukrainian, Swedish, Norwegian, Finnish, and Lao
  • ⚙️ Advanced API Management: Multiple API keys and model switching support with model_settings.json
  • 🛠️ Granular Tool Control: Enable/disable individual MCP tools for precise customization
  • 💡 Custom Instructions: Personalized system prompts for tailored AI behavior
  • ⌨️ Keyboard Shortcuts: Comprehensive hotkey support for efficient navigation and operations (rename, settings, reload, new chat, etc.)
  • 📝 Chat Draft Saving: Automatically saves chat input drafts to prevent data loss
  • 🔄 Auto-Update Mechanism: Automatically checks for and installs the latest application updates
  • 🔐 MCP Server Authentication: Added support for MCP server authentication

    ⚠️ Note: This feature is currently unstable and may require frequent re-authorization

  • 🛠️ Built-in Local Tools: Pre-configured tools available out of the box - Fetch (web requests), File Manager (read/write files), and Bash (command execution)
  • 🤖 MCP Server Installer Agent: Intelligent agent that helps you install and configure MCP servers automatically
  • 🔔 Multiple Elicitation Support: Handle multiple MCP elicitation requests simultaneously in the UI
  • 📁 @ File Path Search: Extended @ keyword in chat input to search file paths

Recent updates(2026/02/26) - v0.14.0+ 🎉

  • 🛠️ Skills & Slash Commands: Support skills and more slash commands
  • 🔍 Chat History Search: Support chat history search

Platform Availability

Platform Electron Tauri
Windows ✅ ✅
macOS ✅ 🔜
Linux ✅ ✅

Migration Note: Existing local MCP/LLM configurations remain fully supported. OAP integration is additive and does not affect current workflows.

Download and Install ⬇️

Get the latest version of Dive: Download

Windows users: 🪟

Choose between two architectures:

  • Tauri Version (Recommended): Smaller installer (<30MB), modern architecture
  • Electron Version: Traditional architecture, fully stable
  • Python and Node.js environments will be downloaded automatically after launching

MacOS users: 🍎

  • Electron Version: Download the .dmg version
  • You need to install Python and Node.js (with npx uvx) environments yourself
  • Follow the installation prompts to complete setup

Linux users: 🐧

Choose between two architectures:

  • Tauri Version: Modern architecture with smaller installer size
  • Electron Version (Recommended): Traditional architecture with .AppImage format
  • You need to install Python and Node.js (with npx uvx) environments yourself
  • For Ubuntu/Debian users:
    • You may need to add --no-sandbox parameter
    • Or modify system settings to allow sandbox
    • Run chmod +x to make the AppImage executable
  • For Arch users:
    • If you are using Arch Linux, you can install dive using an AUR helper. For example: paru -S dive-ai

MCP Setup Options

For more detailed instructions, please see MCP Servers Setup.

The easiest way to get started! Access enterprise-grade MCP tools instantly:

  1. Sign up at OAPHub.ai
  2. Connect to Dive using one-click deep links or configuration files
  3. Enjoy managed MCP servers with zero setup - no Python, Docker, or complex dependencies required

Benefits:

  • ✅ Zero configuration needed
  • ✅ Cross-platform compatibility
  • ✅ Enterprise-grade reliability
  • ✅ Automatic updates and maintenance

Build 🛠️

See BUILD.md for more details.

Contributing 🤝

We welcome contributions from the community! Here's how you can help:

Development Setup

  1. Fork the repository
  2. Clone your fork: git clone https://github.com/YOUR_USERNAME/Dive.git
  3. Install dependencies: npm install
  4. Start development: npm run dev (Electron) or cargo tauri dev (Tauri)
  5. Make your changes and test thoroughly
  6. Submit a pull request

License 📄

Dive is open-source software licensed under the MIT License.

Connect With Us 🌐

Frequently asked questions

Is Dive free to use?

Dive is open source under the MIT licence. There is no licence fee and no seat count — you can self-host it or, where the project offers one, pay a vendor for a managed version instead.

What does Dive do?

Dive is an open-source MCP Host Desktop Application that seamlessly integrates with any LLMs supporting function calling capabilities. ✨

What is Dive written in?

Dive is primarily written in TypeScript. Its source is publicly available at https://github.com/OpenAgentPlatform/Dive, and it has 1,827 GitHub stars.