Skip to main content
📖 The AI Tool Bible

AionUi

Open-source desktop cowork app that unifies 20+ AI coding agents and CLI models in a single graphical workspace.

Free· Free and open-source under Apache-2.0. You bring your own API keys (Gemini, Claude, OpenAI, Qwen, DeepSeek, etc.) and pay each provider directly, or run local models via Ollama or LM Studio at zero token cost.AgentsModel-agnostic: routes to Claude, GPT-4/5, Gemini, DeepSeek, Qwen, Kimi, plus local Ollama and LM Studio runtimes and any OpenAI-compatible endpoint.
Visit website →
Best for

Developers and power users who already work with multiple CLI AI agents and want a single local, privacy-preserving desktop cockpit to run them in parallel across cloud and local models.

Skip if

Non-technical users who want a hosted chat product, or teams that need centralised admin, SSO, and audit logs — AionUi is a personal desktop app, not an enterprise platform.

AionUi is a free, open-source desktop application that turns terminal-based AI agents into a unified graphical cowork environment. Instead of juggling separate terminal windows for Claude Code, Gemini CLI, Codex, Qwen Code, and every other CLI agent you have installed, AionUi auto-detects them and exposes each as a tab or panel inside a single desktop workspace. Sessions run in parallel, contexts are preserved per conversation, and everything — chat history, credentials, task state — stays in a local SQLite database on your machine rather than a vendor's cloud.

Beyond wrapping CLIs, AionUi ships its own built-in agent engine so you can start working immediately without installing anything else. It supports 30+ model providers: OpenAI, Anthropic, Google, DeepSeek, AWS Bedrock, Qwen, Kimi, Baidu, plus local runtimes (Ollama, LM Studio) and any OpenAI-compatible custom endpoint. On top of raw chat it adds practical productivity primitives — smart file management (batch renaming, auto-organisation, classification), a scheduled-tasks system where natural-language instructions like 'every morning at 9am, summarise yesterday's git commits' are translated into cron jobs bound to a live conversation, and a library of 21 pre-built assistants for slides, Word docs, Excel analysis, and academic writing.

A remote WebUI mode plus Telegram, Lark, DingTalk, and WeChat bridges let you talk to your desktop agents from a phone or another laptop while all execution stays on the host machine. Typical users are developers and power users who already live in Claude Code or Gemini CLI, want a nicer UI, care about keeping conversation data local, and want to switch between models mid-task without re-plumbing config files. It runs on macOS, Windows, and Linux.

Editor's take

AionUi is the answer to 'I have Claude Code and Gemini CLI and Codex all open in different terminals and I hate my life.' It's not trying to be an IDE; it's a well-scoped orchestration shell that respects local-first storage and BYO-keys. The scheduled-tasks-bound-to-a-conversation pattern is genuinely clever, and Apache-2.0 means you can bend it to your workflow.

— The AI Tool Bible editorial team

Pros

  • One interface for 20+ CLI agents (Claude Code, Codex, Gemini CLI, Qwen Code, etc.) with auto-detection.
  • Fully local storage in SQLite — no chat history, code, or credentials sent to a vendor.
  • Bring-your-own-key across 30+ providers, including local Ollama and LM Studio for zero-cost inference.
  • Multi-session parallelism keeps contexts separated so long tasks don't collide.
  • Natural-language scheduled tasks compile to cron and stay bound to their originating conversation.
  • Remote WebUI plus Telegram/Lark/DingTalk/WeChat bridges for controlling your desktop agents from anywhere.
  • Apache-2.0 licensed and actively maintained; free forever with no upsell tier.

Cons

  • ⚠️ Desktop-only architecture — no hosted SaaS option, so you must run it on a machine you control.
  • ⚠️ Value depends on the underlying CLIs and APIs you configure; setting up keys and local models is on you.
  • ⚠️ Feature surface is broad (agents, files, scheduling, assistants) which can feel busy compared to focused single-purpose IDE integrations.
  • ⚠️ Documentation and UI polish trail commercial IDE assistants like Cursor or Copilot.
  • ⚠️ Chinese-market model integrations (Kimi, Baidu, Qwen) are more prominent than Western users may need, adding surface area they won't use.

Use cases

Unified control panel for multiple CLI coding agentsLocal-first AI chat with private SQLite historyParallel multi-agent task executionScheduled recurring AI jobs via natural languageBatch file renaming and auto-organisationExcel data analysis and report generationSlide, Word, and academic-paper draftingRemote access to local models from mobile via Telegram or WebUIRunning Ollama or LM Studio models through a polished GUI

Explore related

Compare with similar tools

All in Agents

LangGraph

Featured
Agents · BYO (Claude / GPT / open)
8.8

Stateful, graph-based agent orchestration from LangChain.

Freemium· Developer: $0 / seat per month · Plus: $39 / seat per month · Enterprise: Custom pricingstateful agentshuman-in-loop

CrewAI

Featured
Agents · BYO (Claude / GPT / open)
8.4

Python framework for multi-agent orchestration.

Freemium· Basic: Free · Enterprise: Custommulti-agentorchestration

Ernie Bot

Agents · Baidu ERNIE 4.0 / ERNIE X1 / ERNIE Turbo (in-house)
8.7

Baidu's Mandarin-first ChatGPT rival, powered by the ERNIE model family

Freemium· Free tier for Ernie 3.5 access; Ernie 4.0 and premium features require a paid subscription (approximately CNY 59.9/month for individual plans); enterprise API pricing via Baidu AI Cloud Qianfan platform is metered per 1K tokens.Mandarin content writing and marketing copyChinese-language document Q&A and summarisation

Moveworks

Agents · Orchestrates multiple enterprise-ready LLMs (undisclosed mix, historically including OpenAI GPT and in-house models via its Reasoning Engine)
8.7

The enterprise AI assistant that searches, answers, and takes action across your business systems

Enterprise· Enterprise-only pricing; no public tiers. Quoted per organization based on employee count, integrations, and agent scope. Contact sales for a quote.IT service desk ticket deflectionHR policy Q&A and self-service

AWS Bedrock

Agents · Multi-model: Anthropic Claude, Meta Llama, Mistral, Cohere, AI21, Amazon Nova/Titan, DeepSeek, Stability, OpenAI GPT
8.6

Build and scale generative AI applications with foundation models

Paid· Pay-as-you-go per 1K input/output tokens per model; on-demand, batch, and provisioned throughput tiers. New AWS accounts get up to $200 in credits. Enterprise agreements via AWS.Enterprise RAG chatbot over private documentsMulti-step tool-using agents via AgentCore

Claude Agent SDK

Agents · Claude Opus / Sonnet
8.6

Anthropic's official SDK for building autonomous Claude agents.

Free· Free SDK; API usage billed at Claude ratesClaude agentstool use