#66th of 6 in Desktop AI apps

aionui

Desktop and WebUI app that runs a built-in agent plus external CLI agents

Stars
33.5k
License
Apache-2.0
Last commit
Oct 2026
Last release
Sep 2026
Language
TypeScript
Stars, last 29 weeks+14,260
24 Mar 2026: 19,257 stars31 Mar 2026: 19,933 stars7 Apr 2026: 20,524 stars14 Apr 2026: 21,184 stars21 Apr 2026: 21,685 stars28 Apr 2026: 22,143 stars5 May 2026: 23,181 stars12 May 2026: 24,259 stars19 May 2026: 25,252 stars26 May 2026: 26,130 stars2 Jun 2026: 26,866 stars9 Jun 2026: 27,395 stars16 Jun 2026: 27,855 stars23 Jun 2026: 28,235 stars30 Jun 2026: 28,642 stars7 Jul 2026: 29,029 stars14 Jul 2026: 29,633 stars21 Jul 2026: 30,196 stars28 Jul 2026: 30,630 stars4 Aug 2026: 31,075 stars11 Aug 2026: 31,555 stars18 Aug 2026: 31,837 stars25 Aug 2026: 32,065 stars1 Sept 2026: 32,305 stars8 Sept 2026: 32,535 stars15 Sept 2026: 32,722 stars22 Sept 2026: 32,942 stars29 Sept 2026: 33,156 stars6 Oct 2026: 33,304 stars13 Oct 2026: 33,517 stars

19,257 on 24 Mar 202633,517 on 13 Oct 2026

From GitHub's daily star counts.

Checked on GitHub.

Overview

AionUi is a TypeScript desktop app for macOS, Windows and Linux. It bundles an agent engine (aionrs) that reads and writes files, searches the web and calls MCP tools using any of 30+ API providers or local Ollama and LM Studio. It also detects installed CLI agents such as Claude Code, Codex and Qwen Code, runs them in parallel sessions, and is reachable through a WebUI or chat bots, with scheduled tasks.

Who it is for: Users who want one desktop app to drive built-in and CLI coding agents

Strengths

  • Auto-detects installed CLI agents (Claude Code, Codex, Qwen Code and others) in one interface
  • Built-in agent works after pasting an API key, with no separate CLI install
  • Scheduled tasks support cron with timezone, fixed intervals and one-time triggers
  • Remote access via browser WebUI or Telegram, Lark, DingTalk and WeChat bots

Weaknesses

  • Local models are reached through a custom API endpoint, not a bundled runtime
  • Slack, Discord and WeCom channels are listed as coming soon
  • Unattended YOLO mode and permissions vary by selected agent
  • README excerpt gives no RAM, port or hardware requirements

What it needs

  • no GPU
  • Docker
  • Needs Optional CLI agents (Claude Code, Codex, etc.), LLM API key or local Ollama/LM Studio
  • Models: Gemini, OpenAI, Anthropic, AWS Bedrock, Ollama

Also in Desktop AI apps

See all 6
Also in Desktop AI apps
RankProjectScore
1cherry-studioCross-platform desktop chat client for many cloud and local LLM providers Live demo ↗ (opens in a new tab)52.6k starsAGPL-3.077 out of 100
2deep-live-camReal-time webcam face swap from a single source image97.1k starsAGPL-3.075 out of 100
3janDesktop app that runs local models or cloud APIs, with a local server44.9k starscustom license67 out of 100
#4chatboxDesktop and mobile chat client for OpenAI, Claude, Gemini and Ollama models42k starsGPL-3.064 out of 100
#5dsh-desktopNative Windows and macOS desktop client for DeepSeek Harness30.8k starsMIT64 out of 100