Desktop app for every LLM provider, one window

cherry-studio leads with a score of 92. Updated from public GitHub data.

Full category: Desktop AI apps.

Which one?

1st pickcherry-studio
Desktop client for chatting with many LLM providers, with agents and knowledge bases
Score 92 · 53.6k stars · AGPL-3.0
Switch toairi
AI VTuber companion with VRM and Live2D avatars, voice, and game-playing
for a permissive license (MIT) · Score 92 · 51.5k stars · MIT
Switch todsh-desktop
Native Windows and macOS desktop client for DeepSeek Harness, built on plugins
for a permissive license (MIT) · Score 91 · 36.3k stars · MIT
Desktop app for every LLM provider, one window
RankProjectAdoptionFreshnessMaintenanceAgent-readyScore
1cherry-studioDesktop client for chatting with many LLM providers, with agents and knowledge bases53.6k starsAGPL-3.0last commit Nov 202696100848592 out of 100
2airiAI VTuber companion with VRM and Live2D avatars, voice, and game-playing Live demo ↗ (opens in a new tab)51.5k starsMITlast commit Nov 202692100858592 out of 100
3dsh-desktopNative Windows and macOS desktop client for DeepSeek Harness, built on plugins36.3k starsMITlast commit Nov 202689100868591 out of 100

Momentum, Verified build, Docs and Privacy are not measured yet; their weight goes to the signals shown. A dash means the signal is not scored for that kind of project. Hover a number for its rating in words.

Reviews

192 out of 100

cherry-studio

Desktop client for chatting with many LLM providers, with agents and knowledge bases

53.6k starsAGPL-3.0last commit Nov 2026

Cherry Studio is an Electron-style desktop app for Windows, macOS and Linux that connects to cloud providers (OpenAI, Anthropic, Gemini, custom compatible endpoints) and local models via Ollama and LM Studio. It adds agents with tool permissions, Skills and MCP servers, local knowledge bases, image generation, translation and an API Gateway. Conversation history and knowledge bases stay on the device, with local and WebDAV backup.

Strengths

  • Supports many cloud providers plus Ollama and LM Studio in one app
  • Agents can use files, commands, browser automation, Skills and MCP servers
  • Local knowledge bases from files, folders and web pages, with OCR options
  • Runs on Windows, macOS and Linux; mobile apps exist for iOS and Android

Weaknesses

  • AGPL-3.0; a commercial license is needed to avoid AGPL terms
  • Centralized management and access controls are in the separate Enterprise Edition
  • Many features need API keys, downloaded models or extra dependencies
  • Community themes written for v1 need adaptation for the v2 interface
  • GPU optional
  • Needs Ollama (optional), LM Studio (optional), Provider API keys (for cloud models)
  • Models: OpenAI, Anthropic, Gemini, Ollama, LM Studio
292 out of 100

airi

AI VTuber companion with VRM and Live2D avatars, voice, and game-playing

Live demo ↗ (opens in a new tab)51.5k starsMITlast commit Nov 2026

AIRI is a TypeScript/Vue monorepo for an animated AI character modeled on Neuro-sama, with VRM and Live2D bodies, speech input and multi-provider TTS. It ships as a browser PWA, an Electron desktop app and an iOS Capacitor app. The character can chat on Discord and Telegram and play Minecraft and Factorio, using hosted LLM APIs or local servers such as Ollama, vLLM and SGLang.

Strengths

  • Runs as browser PWA, desktop app (Windows, macOS, Linux) and iOS app
  • Supports 25+ LLM providers via xsai, including Ollama, vLLM and SGLang
  • VRM and Live2D avatars with auto blink, look-at and idle eye movement
  • Desktop build uses CUDA or Apple Metal through candle without extra setup

Weaknesses

  • README describes development as early stage; plugin system is WIP
  • Memory system (Memory Alaya) and in-browser WebGPU inference are unfinished on the roadmap
  • Game-playing is uneven: Factorio is WIP and Helldivers 2 co-play is not done
  • No Docker or compose files; self-hosting means building the pnpm monorepo or using releases
  • GPU optional
  • Needs Node.js, pnpm
  • Models: OpenAI, Anthropic Claude, Google Gemini, DeepSeek, Ollama
391 out of 100

dsh-desktop

Native Windows and macOS desktop client for DeepSeek Harness, built on plugins

36.3k starsMITlast commit Nov 2026

Wraps the pinned upstream DeepSeek Harness local Web UI, host service and plugin system in a desktop app with window, tray, terminal, auto-update and work profiles. The desktop shell is itself a DSH plugin. It includes a plugin market and phone remote control (2.0.9 and later). Installers cover Windows x64 and macOS Universal, and no Node.js install is needed.

Strengths

  • Installers for Windows x64 and macOS Universal; the app starts and manages the local Harness service
  • Runs a pinned, unmodified upstream version, with desktop features added as plugins
  • Built-in plugin market and iOS/Android remote control from 2.0.9
  • Web service listens on loopback only by default

Weaknesses

  • No Linux build listed
  • Optional LAN access has no authentication; anyone on the network can operate the machine
  • Independent community project, not affiliated with DeepSeek; tied to the pinned upstream version
  • Update checks send version, channel and a persistent random installation ID
  • Needs DeepSeek Harness (bundled, pinned)
  • Models: unknown