Agent IDE that enables you to manage fleets of coding agents. It comes with an agentic orchestrator that plans tasks, spawns agents, and autonomously handles CI fixes, merge conflicts, and code reviews.
Agent Orchestrator is a TypeScript CLI tool, installable as `@aoagents/ao`, that manages fleets of AI coding agents working in parallel across a codebase. Each agent receives an isolated git worktree, its own branch, and its own pull request, then works autonomously through the full development cycle: writing code, creating PRs, fixing CI failures, and addressing reviewer comments without human intervention unless judgment is specifically required. The system connects to Claude Code as its default agent backend (alongside Codex and Aider as alternatives), runs under tmux on macOS and Linux or native ConPTY on Windows, and integrates with GitHub and Linear for issue tracking. A web dashboard at localhost:3000 provides a single supervision point for all active agents. The orchestrator itself is configured via a YAML file and uses the `ao` CLI internally to manage sessions. Developers maintaining large backlogs of issues or engineering teams running parallel feature work are the primary audience, and a notable detail is that the project used the system to build itself.
- ✓Open-source license (MIT)
- ✓Actively maintained (<30d)
- ✓Healthy fork ratio
- ✓Clear description
- ✓Topics declared
- ✓Documented (README)
git clone https://github.com/AgentWrapper/agent-orchestrator && cp agent-orchestrator/*.md ~/.claude/agents/4 items in this repository
Open-source, pluggable agentic coding orchestrator. Manages durable coding agents (Claude Code, Codex, OpenCode) through a simple interface — spawn agents, track progress, and let feedback loops like PR reviews and CI failures automatically route to the right agents. Use for fixing bugs, building features, working on GitHub issues, checking status, and managing agent sessions.
Triage bugs reported in chat/issues, search for duplicates, file or update GitHub issues with full context, and push fix PRs.
Generate the weekly Agent Orchestrator release notes. Runs every Thursday 10:00 IST from the bot cron, or on-demand. Queries the GitHub API for the latest release, merged PRs, commits, contributors, and star counts, and produces a publishable markdown post in the house style. Output is posted to Discord by the cron job after this skill returns.
Draft viral social media posts for X (Twitter) and LinkedIn. Use when asked to write, draft, create, or improve posts for X, Twitter, LinkedIn, or social media. Handles single posts, threads, milestone celebrations, product launches, hot takes, and engagement-optimized content. NOT for: scheduling posts, managing accounts, or analytics.
Subagents overview
<div align="center">
<img src="assets/ao-logo.svg" alt="Agent Orchestrator" width="160" height="160" />
# Agent Orchestrator
**The orchestration layer for parallel AI coding agents**
[](https://github.com/AgentWrapper/agent-orchestrator/stargazers)
[](https://github.com/AgentWrapper/agent-orchestrator/graphs/contributors)
[](https://x.com/aoagents)
[](https://discord.com/invite/UZv7JjxbwG)
[](LICENSE)
An Agentic IDE that supervises parallel AI coding agents in isolated workspaces, with complete control and automatic feedback loops from CI failures, review comments, and merge conflicts.
<img src="docs/assets/readme/dashboard.png" alt="Agent Orchestrator dashboard showing parallel coding agent sessions" width="100%" />
</div>
---
## What is Agent Orchestrator?
Agent Orchestrator is a meta-harness agent IDE for running AI coding agents in parallel. It gives terminal-based agents like Claude Code, Codex, Cursor, Kimi Code, opencode, and others a shared workspace where their sessions, terminals, branches, pull requests, and feedback loops can be supervised from one place.
The agents still do the coding. AO provides the harness around them: isolated workspaces, live terminal access, session state, PR awareness, and automatic loops that send CI failures, review comments, and merge conflicts back to the right agent. Instead of manually coordinating a pile of agent terminals, AO turns parallel agent work into a managed workflow.
## Why Agent Orchestrator?
AI coding agents become much more useful when they can work in parallel, but parallel work gets messy quickly. Branches overlap, terminals get lost, CI failures need follow-up, review comments need replies, and merge conflicts have to reach the right worker.
Agent Orchestrator is built to keep that loop visible and manageable. It helps you:
- Start multiple agents from the same project without mixing their work
- Keep every session in a separate git worktree
- See which agents are working, waiting, finished, or blocked
- Route CI failures, review comments, and merge conflicts back to the right session
- Use different agent CLIs through one common supervisor
## How it works
At a high level, Agent Orchestrator follows a simple loop:
1. Add a project you want agents to work on.
2. Start one or more sessions from the desktop app or CLI.
3. AO creates an isolated git worktree for each session.
4. AO launches the selected coding agent in that session's terminal runtime.
5. The local daemon watches session state, terminal activity, pull requests, CI, and review feedback.
6. The desktop app and CLI show the current state and let you send follow-up instructions to the right session.
The result is a local control layer for agentic coding: agents still do the coding, while Agent Orchestrator keeps their workspaces, status, terminals, and feedback loops organized.
## Features
The desktop app is the main control surface: projects on the left, active sessions in the center, and the selected session's terminal, pull request state, review runs, and browser preview in the inspector.
<table>
<tr>
<td width="36%">
<h3>Parallel agent sessions</h3>
<p>Start multiple coding agents from the same project without mixing files, branches, terminals, or pull request state.</p>
</td>
<td width="64%">
<img src="docs/assets/readme/dashboard.png" alt="Agent Orchestrator board with multiple parallel sessions" />
</td>
</tr>
<tr>
<td width="36%">
<h3>Live terminal control</h3>
<p>Open any session and attach to the worker terminal while keeping session summary, PR state, and follow-up actions in view.</p>
</td>
<td width="64%">
<img src="docs/assets/readme/session-terminal.png" alt="Session terminal inside Agent Orchestrator" />
</td>
</tr>
<tr>
<td width="36%">
<h3>Review feedback loop</h3>
<p>Run reviewer agents, inspect review status, and route requested changes back to the right worker session.</p>
</td>
<td width="64%">
<img src="docs/assets/readme/reviews-tab.png" alt="Reviews tab showing reviewer runs and actions" />
</td>
</tr>
<tr>
<td width="36%">
<h3>In-app browser preview</h3>
<p>Preview a session's local app beside the terminal so UI work, browser state, and agent output stay together.</p>
</td>
<td width="64%">
<img src="docs/assets/readme/browser-preview.png" alt="Browser preview tab showing a local app preview" />
</td>
</tr>
</table>
## Supported Agents
AO ships adapters for 23 worker agent harnesses:
<p>
<a href="https://aoagents.dev/docs/plugins/agents/claude-code"><img src="frontend/src/landing/public/docs/logos/claude-code.svg" alt="" width="16" height="16" valign="middle" /> <code>claude-code</code></a> ·
<a href="https://aoagents.dev/docs/plugins/agents/codex"><img src="frontend/src/landing/public/docs/logos/codex.svg" alt="" width="16" height="16" valign="middle" /> <code>codex</code></a> ·
<a href="https://aoagents.dev/docs/plugins/agents/aider"><img src="frontend/src/landing/public/docs/logos/aider.png" alt="" width="16" height="16" valign="middle" /> <code>aider</code></a> ·
<a href="https://aoagents.dev/docs/plugins/agents/opencode"><img src="frontend/src/landing/public/docs/logos/opencode.svg" alt="" width="16" height="16" valign="middle" /> <code>opencode</code></a> ·
<a href="https://aoagents.dev/docs/plugins/agents"><img src="frontend/src/landing/public/docs/logos/grok.png" alt="" width="16" height="16" valign="middle" /> <code>grok</code></a> ·
<a href="https://aoagents.dev/docs/plugins/agents"><img src="frontend/src/landing/public/docs/logos/droid.png" alt="" width="16" height="16" valign="middle" /> <code>droid</code></a> ·
<a href="https://aoagents.dev/docs/plugins/agents"><code>amp</code></a> ·
<a href="https://aoagents.dev/docs/plugins/agents"><code>agy</code></a> ·
<a href="https://aoagents.dev/docs/plugins/agents"><img src="frontend/src/landing/public/docs/logos/crush.png" alt="" width="16" height="16" valign="middle" /> <code>crush</code></a> ·
<a href="https://aoagents.dev/docs/plugins/agents/cursor"><img src="frontend/src/landing/public/docs/logos/cursor.svg" alt="" width="16" height="16" valign="middle" /> <code>cursor</code></a> ·
<a href="https://aoagents.dev/docs/plugins/agents"><img src="frontend/src/landing/public/docs/logos/qwen.png" alt="" width="16" height="16" valign="middle" /> <code>qwen</code></a> ·
<a href="https://aoagents.dev/docs/plugins/agents"><img src="frontend/src/landing/public/docs/logos/copilot.png" alt="" width="16" height="16" valign="middle" /> <code>copilot</code></a> ·
<a href="https://aoagents.dev/docs/plugins/agents"><img src="frontend/src/landing/public/docs/logos/goose.png" alt="" width="16" height="16" valign="middle" /> <code>goose</code></a> ·
<a href="https://aoagents.dev/docs/plugins/agents"><code>auggie</code></a> ·
<a href="https://aoagents.dev/docs/plugins/agents"><img src="frontend/src/landing/public/docs/logos/continue.png" alt="" width="16" height="16" valign="middle" /> <code>continue</code></a> ·
<a href="https://aoagents.dev/docs/plugins/agents"><img src="frontend/src/landing/public/docs/logos/devin.png" alt="" width="16" height="16" valign="middle" /> <code>devin</code></a> ·
<a href="https://aoagents.dev/docs/plugins/agents"><code>cline</code></a> ·
<a href="https://aoagents.dev/docs/plugins/agents"><img src="frontend/src/landing/public/docs/logos/kimi.png" alt="" width="16" height="16" valign="middle" /> <code>kimi</code></a> ·
<a href="https://aoagents.dev/docs/plugins/agents"><img src="frontend/src/landing/public/docs/logos/kiro.png" alt="" width="16" height="16" valign="middle" /> <code>kiro</code></a> ·
<a href="https://aoagents.dev/docs/plugins/agents"><img src="frontend/src/landing/public/docs/logos/kilocode.png" alt="" width="16" height="16" valign="middle" /> <code>kilocode</code></a> ·
<a href="https://aoagents.dev/docs/plugins/agents"><img src="frontend/src/landing/public/docs/logos/vibe.png" alt="" width="16" height="16" valign="middle" /> <code>vibe</code></a> ·
<a href="https://aoagents.dev/docs/plugins/agents"><img src="frontend/src/landing/public/docs/logos/pi.png" alt="" width="16" height="16" valign="middle" /> <code>pi</code></a> ·
<a href="https://aoagents.dev/docs/plugins/agents"><code>autohand</code></a>
</p>
Reviewer agents are configured separately. The current reviewer harnesses are:
<p>
<a href="https://aoagents.dev/docs/plugins/agents/claude-code"><img src="frontend/src/landing/public/docs/logos/claude-code.svg" alt="" width="16" height="16" valign="middle" /> <code>claude-code</code></a> ·
<a href="https://aoagents.dev/docs/plugins/agents/codex"><img src="frontend/src/landing/public/docs/logos/codex.svg" alt="" width="16" height="16" valign="middle" /> <code>codex</code></a> ·
<a href="https://aoagents.dev/docs/plugins/agents/opencode"><img src="frontend/src/landing/public/docs/logos/opencode.svg" alt="" width="16" height="16" valign="middle" /> <code>opencode</code></a>
</p>
**If it runs in a terminal, it runs on Agent Orchestrator.**
## Install
Download the latest desktop build for your platform:
| Platform | Download |
| --------------------- | ----------------------------------------------------------------------------------------------------------------------------- |
| macOS (Apple silicoWhat people ask about agent-orchestrator
What is AgentWrapper/agent-orchestrator?
+
AgentWrapper/agent-orchestrator is subagents for the Claude AI ecosystem. Agent IDE that enables you to manage fleets of coding agents. It comes with an agentic orchestrator that plans tasks, spawns agents, and autonomously handles CI fixes, merge conflicts, and code reviews. It has 8.6k GitHub stars and was last updated today.
How do I install agent-orchestrator?
+
You can install agent-orchestrator by cloning the repository (https://github.com/AgentWrapper/agent-orchestrator) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is AgentWrapper/agent-orchestrator safe to use?
+
Our security agent has analyzed AgentWrapper/agent-orchestrator and assigned a Trust Score of 100/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.
Who maintains AgentWrapper/agent-orchestrator?
+
AgentWrapper/agent-orchestrator is maintained by AgentWrapper. The last recorded GitHub activity is from today, with 452 open issues.
Are there alternatives to agent-orchestrator?
+
Yes. On ClaudeWave you can browse similar subagents at /categories/agents, sorted by popularity or recent activity.
Deploy agent-orchestrator to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/agentwrapper-agent-orchestrator)<a href="https://claudewave.com/repo/agentwrapper-agent-orchestrator"><img src="https://claudewave.com/api/badge/agentwrapper-agent-orchestrator" alt="Featured on ClaudeWave: AgentWrapper/agent-orchestrator" width="320" height="64" /></a>More Subagents
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
The agent that grows with you
Java 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
The agent engineering platform.
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.