Feedback: ORCH — CLI orchestrator for running multi-agent Continue teams

[oxgeneral]

Hey Continue community!

Sharing a tool I built that works alongside Continue for multi-agent projects: ORCH (https://github.com/oxgeneral/ORCH)

The problem: When you run Continue alongside Claude Code, Codex, or other AI agents on a real project — they conflict on files, you manually copy-paste context between terminals, and there is no coordination layer.

ORCH is an open-source CLI runtime that orchestrates teams of AI coding agents:

• Typed task queue — state machine: todo → in_progress → review → done, with automatic retries on stalls
• Scope locking — prevents two agents from editing the same file simultaneously
• Inter-agent messaging — agents share results programmatically (no human copy-paste)
• Adapter system — Continue, Claude Code, Codex, Cursor all connect as named adapters
• TUI dashboard — live view of all running agents, tasks, and logs
• Goals system — high-level objectives auto-decomposed into agent subtasks

Quick start:

npm install -g @oxgeneral/orch
orch agent add "Continue" --adapter shell
orch task add "Refactor database layer" --assignee <agent-id>
orch tui

1,647 passing tests, TypeScript strict, zero-database (YAML/JSON files only), MIT license.
https://github.com/oxgeneral/ORCH

Happy to hear how Continue users are running multi-agent setups and whether ORCH could help!