AionUi is an open-source desktop multi-agent harness and orchestrator developed by iOfficeAI. It serves as a unified workspace for managing, scheduling, and orchestrating both built-in specialized assistants and local terminal-based coding agents on a single machine. In day-to-day operations, AionUi auto-detects locally installed AI tools such as Claude Code, Codex, Gemini CLI, Goose, and Aion CLI. Developers interact via a desktop application or embedded WebUI, dispatching tasks to individual agents or coordinating multi-agent parallel workflows. Model configuration is decentralized and bring-your-own-key (BYOK); users connect directly to OpenAI, Anthropic, or custom OpenAI-compatible endpoints with model-to-agent granularity and no proxying. Unlike single-process CLI coding tools, AionUi focuses on agent teaming, background task automation, and remote accessibility. It features a built-in cron scheduler for recurring tasks (such as automated daily code reviews or backups), cross-platform messaging integrations for remote agent triggering, and standard support for Model Context Protocol (MCP) servers and modular skills.
Local Agent Auto-Detection — Automatically identifies and orchestrates installed CLI agents like Claude Code, Codex, Gemini CLI, and Goose. - Multi-Agent Teaming — Assigns subtasks across multiple parallel agent instances within a single coordinated project workflow. - Direct BYOK Model Integration — Configures unproxied API connections to any provider or self-hosted endpoint with independent model mapping per agent. - Cron-Based Task Scheduling — Runs background 24/7 automations for recurring actions such as automated code reviews, backups, and data processing. - Multi-Channel Remote Control — Dispatches prompts and monitors running local agents remotely through Telegram, Slack, Discord, Lark, or WebUI. - Extensible MCP & Skills System — Integrates Model Context Protocol servers and community skills for modular agent tooling.
Use cases
Use Case: Parallel Multi-Agent Feature Development A developer orchestrates a complex task across multiple tools simultaneously. AionUi assigns backend refactoring to Claude Code while running Codex in parallel to generate test suites and an analytical agent to parse project performance metrics.
Use Case: Automated Morning Code and Security Audits A developer configures a recurring cron task in AionUi that triggers Claude Code every morning at 08:00 AM. The agent reviews unstaged branch diffs, checks for style violations, and compiles a Markdown review summary before work begins.
Use Case: Remote Task Execution via Chat Ops An engineer triggers local repository builds and diagnostic scripts while away from their workstation by sending commands through Telegram to AionUi's remote gateway, running the task on the desktop agent and reporting back outputs.
Who it is for
AionUi is designed for developers, technical managers, and power users who use multiple AI CLI tools and need a centralized desktop control plane for parallel orchestration, background scheduling, and remote chat triggers. It is not intended for developers looking strictly for a minimalist, pure terminal-only single agent.
Install guide
Installation Download the desktop binary for your operating system from the official website or GitHub releases, or clone the repository to run from source: bash git clone https://github.com/iOfficeAI/AionUi.git cd AionUi npm install npm run dev
First Run 1. Launch the AionUi desktop application. 2. Open Settings > LLM Config to add your API keys (e.g., Anthropic, OpenAI, or a local endpoint URL). 3. Navigate to Team / Agents to verify auto-detected local CLI tools (e.g., Claude Code, Gemini CLI) or configure custom agent profiles.
Example Session To run a coordinated task across local agents via the AionUi prompt bar: text Plan and execute: Refactor the authentication middleware in ./src/auth and run test coverage checks. AionUi will decompose the prompt, assign code modifications to your designated coding agent (e.g., Claude Code), run test validation in the background, and provide artifact inspection directly within the interface.
Multica — Multica is an open-source AI coding agent harness and orchestration platform developed by multica-ai. It provides a structured runtime architecture…
nanoclaw — nanoclaw is an open-source CLI agent framework and containerized execution harness developed by Nanoco AI. Designed around Claude-powered workflows and…
5dive — 5dive is an open-source agent orchestration harness and management framework developed by 5dive-ai. It provides scaffolding, execution scripts, and infrastructure…
Orkas — Orkas is an open-source desktop agent harness and workflow orchestrator developed by Orkas-AI. Built to bridge autonomous AI execution with…
Nullclaw — Nullclaw is an open-source, lightweight AI coding assistant and agent harness designed to operate with minimal overhead. Developed using Zig…
Hermes Agent — Hermes Agent is an open-source terminal-based AI coding agent developed by NousResearch. Designed to bridge terminal workflows and modern IDE…