by Untrivial-ai · Codex Skill · ★ 12.7k
Agent Orchestrator The orchestration layer for parallel AI coding agents 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. 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
| Stars | 12,739 |
| Forks | 1,758 |
| Language | Go |
| Category | Codex Skill |
| License | Apache-2.0 |
| Quality Score | 66.108432432595/100 |
| Open Issues | 758 |
| Last Updated | 2026-10-04 |
| Created | 2026-02-13 |
| Platforms | browser, claude-code, cli, codex, go |
| Est. Tokens | ~18k |
These tools work well together with agent-orchestrator for enhanced workflows:
Explore other popular codex skill tools:
agent-orchestrator is Run and supervise teams of coding agents from planning to merge. Any harness (Claude code, codex, +25 more). Desktop, web, mobile, and cloud agents.. It is categorized as a Codex Skill with 12.7k GitHub stars.
agent-orchestrator is primarily written in Go. It covers topics such as agent-fleet, agent-ide, agent-orchestration.
You can find installation instructions and usage details in the agent-orchestrator GitHub repository at github.com/Untrivial-ai/agent-orchestrator. The project has 12.7k stars and 1758 forks, indicating an active community.
agent-orchestrator is released under the Apache-2.0 license, making it free to use and modify according to the license terms.