# AI-QL/tuui

A desktop MCP client designed as a tool unitary utility integration, accelerating AI adoption through the Model Context Protocol (MCP) and enabling cross-vendor LLM API orchestration.

Repository: https://github.com/AI-QL/tuui
Canonical: https://ross.abutalabs.com/products/tuui
Homepage: https://www.tuui.com/
Language: TypeScript
License: Apache-2.0
License Family: permissive
Topics: agent, agentic-ai, ai, deepseek, llm, mcp, openai-api, qwen, mcp-client, mcp-host, model-context-protocol, ai-playground, mcp-inspector, llm-eval, prompt, testing, anthropic, claude, dxt, mcpb
Last push: 2026-05-14T09:02:28+00:00

## Health v2 (maintenance only)
Score: 74/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 82, release rhythm 84, longevity 37
- inputs: {"age_days": 519, "days_push": 111, "days_rel": 111, "gap_med": 1, "n_releases_24m": 48}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1153, forks 108 (observed 2026-08-28T04:03:47.325567+00:00)

## What it is
TUUI is an open-source desktop MCP client and local AI playground built with Vue3 and Electron, serving as a unified interface for Model Context Protocol tool integration. It orchestrates cross-vendor LLM APIs (OpenAI, Anthropic, DeepSeek, etc.) without requiring accounts, running locally on Windows, macOS, and Linux.

## Use cases
- test and inspect MCP servers with a desktop client
- chat with LLMs locally using my own API keys across vendors
- playground to evaluate and compare different LLM APIs
- connect AI tools via Model Context Protocol without accounts
- run an MCP host client on Windows, macOS, or Linux
- experiment with MCP tools, prompts, and resources

## When to choose
- you need a free, open-source desktop MCP client with no account requirements
- you want to orchestrate multiple LLM vendors through one interface
- you need to test or inspect MCP servers interactively
- you prefer a local AI playground with full control over your data

## When to avoid
- you need a web-based or team-shared chat deployment
- you want a fully managed hosted AI assistant
- you need MCP roots/client features not yet implemented
- you require a mobile or browser-only client

## Facets
- artifact type: application
- maturity: active
- function: mcp, chat-interface, llm-inference, agent-framework, prompt-engineering, testing, gui, developer-tools
- domain: large-language-models, chatbots, developer-tools, cross-platform, desktop-applications
- platform: windows, cross-platform
- tags: mcp-client, mcp-host, llm-playground, cross-vendor-api-orchestration, vue3, electron-app, openai-api, anthropic, llm-eval, local-ai, ai-agents, macos, linux, desktop, electron, typescript, nodejs

## Member repositories
- AI-QL/tuui (main) score 74

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:47.325567+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:33:24.690823+00:00, confidence not recorded.
  - readme: https://github.com/AI-QL/tuui (fetched 2026-08-28T04:03:47.325567+00:00, sha b98698684f5e)
  - homepage: https://www.tuui.com/ (fetched 2026-08-29T12:38:12.545667+00:00, sha 057c2791378e)
  - site_page: https://www.tuui.com/installation-and-build/getting-started (fetched 2026-08-29T12:38:12.554816+00:00, sha 6d7314ec415d)
- Data as of 2026-08-30T08:39:29.467469+00:00.