mcpField
A
AI as Workspace

AI as Workspace

github.com/NitroRCrChat Apps1.8kUpdated 23w ago

About AI as Workspace

AI as Workspace is a cross-platform, lightweight AI chat client with MCP support. The project is deprecated and succeeded by Nya AI. It suits users who want to organize conversations into workspaces.

Key features

  1. 01Runs on Windows, Linux, macOS, Android and Web
  2. 02Connects to multiple AI providers
  3. 03Nested workspaces and folders for conversations
  4. 04Supports MCP tools, prompts and resources
  5. 05Web search based on SearXNG

Use cases

  1. 01Separating conversations by topic into workspaces
  2. 02Extending chat with tool calls through MCP servers
  3. 03Using the same chat data across several platforms

MCP support

Acts as an MCP client that connects to MCP servers over STDIO and HTTP. MCP servers can be installed from the plugin marketplace or added manually.

Details

From the project README

README image

AI as Workspace

MCP Client MCP client with features

Warning

This project is deprecated and has been succeeded by Nya AI, a complete rewrite with a new tech stack. The new project provides most of the features and consistent experience of this project, along with many new features and optimizations.

For existing users, please refer to Migrating to Nya AI.

An elegant AI client

Web Version - Download - Docs - Self-hosting Guide - 简体中文

README image

Features Overview

Consistent Experience Across All Platforms
  • Supported platforms: Windows, Linux, Mac OS, Android, Web (PWA)
  • Multiple AI providers: OpenAI, Anthropic, Google, DeepSeek, xAI, Azure, etc.
Conversation Interface
  • User input preview
  • Modifications and regenerations presented as branches
  • Customizable keyboard shortcuts
  • Quick scrolling to the beginning/end of a message
README image
Multiple Workspaces
  • Create multiple workspaces to separate conversations by themes
  • Group workspaces into folders; supports nesting
  • Create multiple assistants within a workspace or global assistants
README image
Data Storage
  • Data is stored locally first, accessible offline and loads instantly
  • Cloud synchronization available after login for cross-device syncing
  • Multi-window collaboration: open multiple tabs in the same browser with responsive data synchronization
Design Details
  • Support for text files (code, csv, etc.) as attachments; AI can see file contents and names without occupying display space
  • For large text blocks, use Ctrl + V outside the input box to paste as an attachment; prevents large content from cluttering the display
README image
  • Quote content from previous messages to user inputs for targeted follow-up questions
  • Select multiple lines of message text to copy the original Markdown
README image
  • Automatically wrap code pasted from VSCode in code blocks with language specification
README image
MCP Protocol
  • Support for MCP Tools, Prompts, Resources
  • STDIO and HTTP connection methods
  • Install MCP-type plugins from the plugin marketplace or manually add MCP servers
Web Search
  • Web search based on SearXNG, ready to use out of the box.
  • Also provides the functionality to crawl web content via URL.
  • Supports concurrent search and concurrent crawling.
Artifacts
  • Convert any part of assistant responses into Artifacts
  • User-editable with version control and code highlighting
  • Control assistant read/write permissions for Artifacts
  • Open multiple Artifacts simultaneously
README image
Plugin System
  • Built-in calculator, document parsing, video parsing, image generation plugins
  • Install additional plugins from the marketplace
  • Configure Gradio applications as plugins; compatible with some LobeChat plugins
  • Plugins are more than just tool calling

README image

Lightweight and High Performance
  • Quick startup with no waiting
  • Smooth conversation switching
README image
Dynamic Prompts
  • Create prompt variables using template syntax for dynamic, reusable prompts
  • Extract repetitive parts into workspace variables for prompt reusability
README image
Additional Features

Assistant marketplace, dark mode, customizable theme colors, and more

LightHouse

DesktopMobile
README imageREADME image

Related Projects

  • New API: AI model interface management and distribution system, supporting various large models with OpenAI-compatible format

Install the dependencies

pnpm i
Start the app in development mode (hot-code reloading, error reporting, etc.)
quasar dev
Lint the files
pnpm lint
Build the app for production
# SPA
quasar build

# PWA
quasar build -m pwa

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.