dohooo/helmor

Open-source local workbench for multi-agent software development.

What it solves

Helmor addresses the gap between AI-generated code and actually shipping software. It provides a local-first workbench to orchestrate multiple coding agents in parallel, allowing users to review, test, and merge changes without the friction of switching between different tools and environments.

How it works

Helmor manages isolated git workspaces (using worktrees and branches) for every task under a local directory. Users add a repository, create a workspace, and prompt a chosen agent to perform a task. The workbench integrates a Monaco editor, diff views, and terminals alongside the chat, enabling users to review the agent's work and trigger PR/MR actions (create, merge, fix CI) directly from the interface.

Who it’s for

It is designed for developers who use multiple AI coding agents and want a centralized system to manage parallel tasks, review diffs, and handle the version control lifecycle locally.

Highlights

  • Isolated Workspaces: Each task gets its own git worktree and branch to prevent agents from interfering with each other.
  • Agent Agnostic: Supports various agents including Claude Code, Codex, Cursor, OpenCode, and Kimi Code using the user's own API keys.
  • Integrated Review: Combines conversation, diffs, a code editor, and terminals in a single window.
  • One-Click Shipping: Direct integration with GitHub and GitLab for creating PRs, merging, and resolving conflicts.
  • Scriptable Interface: Includes a CLI and MCP server for terminal-based control or automation by other agents.
  • Quick Access: A floating window (⇧⌥Space) to start workspaces and chats from anywhere.

Related

  • Project
    johannesjo/parallel-code

    A GUI for dispatching multiple AI coding agents in parallel, using git worktrees to isolate each task into its own branch and directory for concurrent development.

  • Project
    preset-io/agor

    A self-hosted, multiplayer web workspace for running coding agents on isolated git branches with dedicated dev environments and cost tracking.

  • Project
    openteams-lab/openteams

    A local-first AI desktop app that provides a shared workspace for multiple coding agents to collaborate, plan, and execute tasks without interfering with each other.

  • Project
    morapelker/hive

    An open-source AI agent orchestrator that allows developers to run multiple AI coding agents in parallel across isolated git worktrees.

  • Project
    Untrivial-ai/agent-orchestrator

    Agent Orchestrator is a cross‑platform desktop app that lets you run multiple LLM‑based coding agents as isolated Git‑backed workers, coordinate them via a project‑level orchestrator, and monitor everything on a live Kanban board.